There exists a trade-off between the depth of field and the image resolution when the depth of field is extended by the wave-front coding method. The trade-off originates from the extension method and the inevitable detector noise. An adaptive imaging system can resolve this by minimizing extension of the depth of field to get the image of the highest resolution. In this paper, a focal plane shift method to minimize the depth extension is introduced and the trade-off relationship and the proposed concept are investigated by simulation. The trade-off is characterized by applying a set of focus measures to depth-extended images, and the proposed concept is verified by some test images.
{"title":"Extending depth of field scheme combined with focal plane shift","authors":"D. Hong, Hyungsuck Cho","doi":"10.1117/12.816477","DOIUrl":"https://doi.org/10.1117/12.816477","url":null,"abstract":"There exists a trade-off between the depth of field and the image resolution when the depth of field is extended by the wave-front coding method. The trade-off originates from the extension method and the inevitable detector noise. An adaptive imaging system can resolve this by minimizing extension of the depth of field to get the image of the highest resolution. In this paper, a focal plane shift method to minimize the depth extension is introduced and the trade-off relationship and the proposed concept are investigated by simulation. The trade-off is characterized by applying a set of focus measures to depth-extended images, and the proposed concept is verified by some test images.","PeriodicalId":91154,"journal":{"name":"Optomechatronic Technologies (ISOT), 2010 International Symposium on : 25-27 Oct. 2010 : [Toronto, ON]. International Symposium on Optomechatronic Technologies (2010 : Toronto, Ont.)","volume":"82 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2008-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88284458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Insufficient vision information such as occlusion, low resolvability, and a small field of view (FOV) represent important issues in microassembly and micromanipulation. In previous research, an active optical system was designed to supply a compact flexible view. However the complex kinematics makes the system operation and calibration much difficult. In this paper, a decoupling design for the variable view image system with a telecentric lens group is proposed to decouple the view angle and scanning mirror angle. The proposed design increases the range of zenith angle. The forward kinematics is analyzed with the help of vector diffraction theory. The singularity of Jacobin is analysis and the singularity configurations are identified. In order to verify the proposed system, a prototype system is built up. A series of experiments on the prototype system shows the validity of the new design.
{"title":"Variable view imaging system with decoupling design","authors":"X. Tao, D. Hong, Hyungsuck Cho","doi":"10.1117/12.816473","DOIUrl":"https://doi.org/10.1117/12.816473","url":null,"abstract":"Insufficient vision information such as occlusion, low resolvability, and a small field of view (FOV) represent important issues in microassembly and micromanipulation. In previous research, an active optical system was designed to supply a compact flexible view. However the complex kinematics makes the system operation and calibration much difficult. In this paper, a decoupling design for the variable view image system with a telecentric lens group is proposed to decouple the view angle and scanning mirror angle. The proposed design increases the range of zenith angle. The forward kinematics is analyzed with the help of vector diffraction theory. The singularity of Jacobin is analysis and the singularity configurations are identified. In order to verify the proposed system, a prototype system is built up. A series of experiments on the prototype system shows the validity of the new design.","PeriodicalId":91154,"journal":{"name":"Optomechatronic Technologies (ISOT), 2010 International Symposium on : 25-27 Oct. 2010 : [Toronto, ON]. International Symposium on Optomechatronic Technologies (2010 : Toronto, Ont.)","volume":"109 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2008-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83631228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present a beam shaping method using deformable mirrors without using a target beam shape. The key to the method is the use of an image-based metric on the quality of beam with respect to the desired attributes of the super-Gaussian output beam. This technique iteratively adjusts the deformable mirror shape to minimize the metric measured using a charge-coupled device camera. Since the algorithm does not use a target beam for the optimization, it produces the resulting super-Gaussian beam geometry consistent with the constraints imposed by the limited stroke and the finite number of actuators of the deformable mirror.
{"title":"Super-Gaussian laser beam shaping using deformable mirrors and intrinsic beam quality metrics","authors":"S. Avino, B. Potsaid, J. Wen","doi":"10.1117/12.816437","DOIUrl":"https://doi.org/10.1117/12.816437","url":null,"abstract":"We present a beam shaping method using deformable mirrors without using a target beam shape. The key to the method is the use of an image-based metric on the quality of beam with respect to the desired attributes of the super-Gaussian output beam. This technique iteratively adjusts the deformable mirror shape to minimize the metric measured using a charge-coupled device camera. Since the algorithm does not use a target beam for the optimization, it produces the resulting super-Gaussian beam geometry consistent with the constraints imposed by the limited stroke and the finite number of actuators of the deformable mirror.","PeriodicalId":91154,"journal":{"name":"Optomechatronic Technologies (ISOT), 2010 International Symposium on : 25-27 Oct. 2010 : [Toronto, ON]. International Symposium on Optomechatronic Technologies (2010 : Toronto, Ont.)","volume":"45 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2008-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75096757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Femtosecond laser technology has the ability to form stable minute grating structures on various materials, including silicon wafers and stainless steel. By forming a periodic structure on a surface of sliding parts, the tribology characteristics can be improved, because the effect of adhesion decreases. Application of a double-pulsed femtosecond laser irradiation technique can generate periodic structures with asymmetric profiles. We previously showed that microparts, such as ceramic chip capacitors and resistors, can be fed along asymmetric surfaces using simple planar symmetric vibrations. Microparts move in one direction because they adhere to these surfaces asymmetrically. In this study, we tested the ability of an asymmetric surface microfabricated by a double-pulsed femtosecond laser irradiation technique to feed 0402-type capacitors (size, 0.4 x 0.2 x 0.2 mm; weight, 0.1 mg). Among the characteristics evaluated were the differences in profiles of the two inclined surfaces, the effect of decreased adhesion, the coefficient of friction in both the forward and the backward directions, and the friction angle of the 0402-type capacitors in both directions. Using the results of feeding experiments of these capacitors, we assessed the relationship between driving frequency and feeding velocity.
飞秒激光技术能够在包括硅片和不锈钢在内的各种材料上形成稳定的微小光栅结构。通过在滑动件表面形成周期性结构，可以改善摩擦特性，因为粘着的影响减小了。应用双脉冲飞秒激光辐照技术可以产生具有非对称轮廓的周期结构。我们之前展示了微部件，如陶瓷芯片电容器和电阻器，可以使用简单的平面对称振动沿着不对称表面馈送。微型部件向一个方向移动，因为它们不对称地附着在这些表面上。在这项研究中，我们测试了通过双脉冲飞秒激光辐照技术微加工非对称表面的能力，以馈送0402型电容器(尺寸，0.4 x 0.2 x 0.2 mm;重量，0.1毫克)。评价了0402型电容器的两个斜面轮廓的差异、粘附降低的影响、前后方向的摩擦系数以及两个方向的摩擦角。利用这些电容器的馈电实验结果，评估了驱动频率与馈电速度之间的关系。
{"title":"Application of asymmetric surface fabricated by femtosecond laser process for microparts feeding","authors":"A. Mitani, S. Hirai","doi":"10.1117/12.807089","DOIUrl":"https://doi.org/10.1117/12.807089","url":null,"abstract":"Femtosecond laser technology has the ability to form stable minute grating structures on various materials, including silicon wafers and stainless steel. By forming a periodic structure on a surface of sliding parts, the tribology characteristics can be improved, because the effect of adhesion decreases. Application of a double-pulsed femtosecond laser irradiation technique can generate periodic structures with asymmetric profiles. We previously showed that microparts, such as ceramic chip capacitors and resistors, can be fed along asymmetric surfaces using simple planar symmetric vibrations. Microparts move in one direction because they adhere to these surfaces asymmetrically. In this study, we tested the ability of an asymmetric surface microfabricated by a double-pulsed femtosecond laser irradiation technique to feed 0402-type capacitors (size, 0.4 x 0.2 x 0.2 mm; weight, 0.1 mg). Among the characteristics evaluated were the differences in profiles of the two inclined surfaces, the effect of decreased adhesion, the coefficient of friction in both the forward and the backward directions, and the friction angle of the 0402-type capacitors in both directions. Using the results of feeding experiments of these capacitors, we assessed the relationship between driving frequency and feeding velocity.","PeriodicalId":91154,"journal":{"name":"Optomechatronic Technologies (ISOT), 2010 International Symposium on : 25-27 Oct. 2010 : [Toronto, ON]. International Symposium on Optomechatronic Technologies (2010 : Toronto, Ont.)","volume":"65 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2008-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75274903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The feasibility to carry out the contactless actuation and control of both continuous facesheet deformable mirrors and MOEMS segmented micromirrors by manipulating van der Waals forces between electrically neutral surfaces is discussed. As we show, appropriately engineering such surface forces allows for adaptive optics strategies that are fully scalable down to the nanostructure level and that are intimately based on the optical properties of the materials involved. Since the magnitude of unretarded van der Waals forces diverges as the third power of the distance between the adaptive surface and the back-facing, actuating boundary, the novel approach proposed herein remains effective as the device size decreases even enabling one to address individual atoms. In some implementations, the actuation mechanism is driven by the dependence of van der Waals forces in semiconductors on illumination. Therefore the possibility exists, with adequate power levels, to design feed-back loops driven exclusively by light. A remarkable property of dispersion forces is their drastic behavior as a function of the topology of the interacting surfaces. This fact, at the frontier of contemporary numerical investigations, leads to the consideration of geometries in which dispersion forces are expected to change from attractive to repulsive. Finally, van der Waals forces exist between all neutral materials and contactless actuation can be achieved, for instance, even if the reflecting surface is not a conductor. This will open new multidimensional parameter space to the use of suitably designed classes of adaptive optics materials, including dielectrics, semiconductors, and multilayered structures, such as photonic-band-gap crystals.
{"title":"Adaptive optics actuation by means of van der Waals forces: a novel nanotechnology strategy to steer light by light","authors":"F. Pinto","doi":"10.1117/12.816474","DOIUrl":"https://doi.org/10.1117/12.816474","url":null,"abstract":"The feasibility to carry out the contactless actuation and control of both continuous facesheet deformable mirrors and MOEMS segmented micromirrors by manipulating van der Waals forces between electrically neutral surfaces is discussed. As we show, appropriately engineering such surface forces allows for adaptive optics strategies that are fully scalable down to the nanostructure level and that are intimately based on the optical properties of the materials involved. Since the magnitude of unretarded van der Waals forces diverges as the third power of the distance between the adaptive surface and the back-facing, actuating boundary, the novel approach proposed herein remains effective as the device size decreases even enabling one to address individual atoms. In some implementations, the actuation mechanism is driven by the dependence of van der Waals forces in semiconductors on illumination. Therefore the possibility exists, with adequate power levels, to design feed-back loops driven exclusively by light. A remarkable property of dispersion forces is their drastic behavior as a function of the topology of the interacting surfaces. This fact, at the frontier of contemporary numerical investigations, leads to the consideration of geometries in which dispersion forces are expected to change from attractive to repulsive. Finally, van der Waals forces exist between all neutral materials and contactless actuation can be achieved, for instance, even if the reflecting surface is not a conductor. This will open new multidimensional parameter space to the use of suitably designed classes of adaptive optics materials, including dielectrics, semiconductors, and multilayered structures, such as photonic-band-gap crystals.","PeriodicalId":91154,"journal":{"name":"Optomechatronic Technologies (ISOT), 2010 International Symposium on : 25-27 Oct. 2010 : [Toronto, ON]. International Symposium on Optomechatronic Technologies (2010 : Toronto, Ont.)","volume":"27 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2008-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80198749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Mirhassani, B. Yousefi, M. Bahadorian, H. T. Shandiz
In this paper a fully automated algorithm for building extraction from remote sensing IKONOS images is presented. Local and global enhancement of an original image improves the rate of building detection in some cases. However, some undesirable effects could occur due to image enhancement. As a result the Bayesian classification method which has been previously used could result in errors. To deal with such problems, decision fusion is used together with a shadow-based verification step to achieve a better result from locally and globally enhanced classified images. Experimental results justify the efficiency of the proposed method in dealing with the problem of building extraction in IKONOS images.
{"title":"Improvement of building extraction using decision fusion of locally and globally enhanced IKONOS images","authors":"S. Mirhassani, B. Yousefi, M. Bahadorian, H. T. Shandiz","doi":"10.1117/12.807592","DOIUrl":"https://doi.org/10.1117/12.807592","url":null,"abstract":"In this paper a fully automated algorithm for building extraction from remote sensing IKONOS images is presented. Local and global enhancement of an original image improves the rate of building detection in some cases. However, some undesirable effects could occur due to image enhancement. As a result the Bayesian classification method which has been previously used could result in errors. To deal with such problems, decision fusion is used together with a shadow-based verification step to achieve a better result from locally and globally enhanced classified images. Experimental results justify the efficiency of the proposed method in dealing with the problem of building extraction in IKONOS images.","PeriodicalId":91154,"journal":{"name":"Optomechatronic Technologies (ISOT), 2010 International Symposium on : 25-27 Oct. 2010 : [Toronto, ON]. International Symposium on Optomechatronic Technologies (2010 : Toronto, Ont.)","volume":"61 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2008-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81470153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Due to the tradeoff between field of view and resolution, the ability of traditional optical telescopes to obtain high-resolution wide field images is limited. This work presents a design for a scanning optical telescope that can produce high resolution images over a wide field of view. This is accomplished by scanning one of the telescope's optical elements. Inherent in such a design is the introduction of optical aberrations as off-axis scanning occurs. The deformable mirror technology is implemented to adaptively correct these aberrations such that on-axis resolution is achieved at off-axis scan angles. The optical design layout is optimized in software to minimize on-axis wavefront aberrations. This paper presents results involving two deformable mirrors based on different technologies: the AgilOptics mirror based on electrostatic actuators and the Imagine Optic mirror based on electromagnetic actuators. Both mirrors are similar in size (about 15mm aperture), but the Imagine Optic mirror has significantly larger actuator displacement, though at a higher cost. The static telescope design has a field of view of 0.49-degrees which is increased to 20-degrees with the AgilOptics mirror and 40-degrees with the Imagine Optic mirror.
{"title":"Off-axis aberration correction for a wide field scanning telescope","authors":"Charles P. Scott, B. Potsaid, J. Wen","doi":"10.1117/12.816439","DOIUrl":"https://doi.org/10.1117/12.816439","url":null,"abstract":"Due to the tradeoff between field of view and resolution, the ability of traditional optical telescopes to obtain high-resolution wide field images is limited. This work presents a design for a scanning optical telescope that can produce high resolution images over a wide field of view. This is accomplished by scanning one of the telescope's optical elements. Inherent in such a design is the introduction of optical aberrations as off-axis scanning occurs. The deformable mirror technology is implemented to adaptively correct these aberrations such that on-axis resolution is achieved at off-axis scan angles. The optical design layout is optimized in software to minimize on-axis wavefront aberrations. This paper presents results involving two deformable mirrors based on different technologies: the AgilOptics mirror based on electrostatic actuators and the Imagine Optic mirror based on electromagnetic actuators. Both mirrors are similar in size (about 15mm aperture), but the Imagine Optic mirror has significantly larger actuator displacement, though at a higher cost. The static telescope design has a field of view of 0.49-degrees which is increased to 20-degrees with the AgilOptics mirror and 40-degrees with the Imagine Optic mirror.","PeriodicalId":91154,"journal":{"name":"Optomechatronic Technologies (ISOT), 2010 International Symposium on : 25-27 Oct. 2010 : [Toronto, ON]. International Symposium on Optomechatronic Technologies (2010 : Toronto, Ont.)","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2008-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90865388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The industry is in need of reliable, computer aided object recognition and localization systems in automation and handling engineering. One possible application is bin picking, i.e. the task of grasping work pieces out of a storage container with a robot. Therefore, the parts do not have to be ordered or semi-ordered but can be totally unordered. 2D image processing techniques often can not perform such sophisticated tasks since the gray scale or color information provided is just not enough. An alternative is the examination of the other dimension. In this paper we discuss a novel approach to a 3D object recognizer that localizes objects by looking at the primitive features within the objects. The basic idea of the system is that the geometric primitives usually carry enough information to make possible proper object recognition and localization. The algorithms use 3D best-fitting combined with clever 2.5D preprocessing. The feasibility of the approach is demonstrated and tested by means of a prototypical bin picking system. The time taken to recognize and localize an object is < 0.5 sec., and the accuracy of the result is in the order of magnitude of the measurements inaccuracy, < 0.5 mm.
{"title":"A novel approach to object recognition and localization in automation and handling engineering","authors":"M. Stotz, J. Kuehnle, A. Verl","doi":"10.1117/12.807337","DOIUrl":"https://doi.org/10.1117/12.807337","url":null,"abstract":"The industry is in need of reliable, computer aided object recognition and localization systems in automation and handling engineering. One possible application is bin picking, i.e. the task of grasping work pieces out of a storage container with a robot. Therefore, the parts do not have to be ordered or semi-ordered but can be totally unordered. 2D image processing techniques often can not perform such sophisticated tasks since the gray scale or color information provided is just not enough. An alternative is the examination of the other dimension. In this paper we discuss a novel approach to a 3D object recognizer that localizes objects by looking at the primitive features within the objects. The basic idea of the system is that the geometric primitives usually carry enough information to make possible proper object recognition and localization. The algorithms use 3D best-fitting combined with clever 2.5D preprocessing. The feasibility of the approach is demonstrated and tested by means of a prototypical bin picking system. The time taken to recognize and localize an object is < 0.5 sec., and the accuracy of the result is in the order of magnitude of the measurements inaccuracy, < 0.5 mm.","PeriodicalId":91154,"journal":{"name":"Optomechatronic Technologies (ISOT), 2010 International Symposium on : 25-27 Oct. 2010 : [Toronto, ON]. International Symposium on Optomechatronic Technologies (2010 : Toronto, Ont.)","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2008-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76443165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chika Aminaka, F. Oohira, Takaki Suzuki, E. Majima
We proposed a fabrication method of a sub-micron gap liquid chromatography micro chip by Silicon micromachining technology and performed a principle confirmation using this chip. This paper shows the fabrication process of the sub-micron gap in the flow channel which is made by the micro-pillar array formation by Silicon micromachining technology, and the deposition of poly-Si and successive thermal oxidation. It has become possible to fabricate the sub-micron order gap and control the gaps by the proposed method. Next, we deposited the ODS (octadecylsily) in the flow channel. Finally, using this chip, we performed the principle confirmation experiment of ODS deposition effect by injecting lysozyme into the flow channel. As the result, it was confirmed that the proposed method has the possibility of the separation analysis of biological samples.
{"title":"Fabrication and characteristic evaluation of sub-micron gap liquid chromatography micro chip","authors":"Chika Aminaka, F. Oohira, Takaki Suzuki, E. Majima","doi":"10.1117/12.807246","DOIUrl":"https://doi.org/10.1117/12.807246","url":null,"abstract":"We proposed a fabrication method of a sub-micron gap liquid chromatography micro chip by Silicon micromachining technology and performed a principle confirmation using this chip. This paper shows the fabrication process of the sub-micron gap in the flow channel which is made by the micro-pillar array formation by Silicon micromachining technology, and the deposition of poly-Si and successive thermal oxidation. It has become possible to fabricate the sub-micron order gap and control the gaps by the proposed method. Next, we deposited the ODS (octadecylsily) in the flow channel. Finally, using this chip, we performed the principle confirmation experiment of ODS deposition effect by injecting lysozyme into the flow channel. As the result, it was confirmed that the proposed method has the possibility of the separation analysis of biological samples.","PeriodicalId":91154,"journal":{"name":"Optomechatronic Technologies (ISOT), 2010 International Symposium on : 25-27 Oct. 2010 : [Toronto, ON]. International Symposium on Optomechatronic Technologies (2010 : Toronto, Ont.)","volume":"76 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2008-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85978564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Face detection and recognition depend strongly on illumination conditions. In this paper, we present improvements in two illumination compensation methods for face recognition. Using genetic algorithms (GA) we select parameters of the Discrete Cosine Transform (DCT) and Local Normalization (LN) methods to improve face recognition. In the DCT method all low frequency components within an isosceles triangle, of side Ddis, are eliminated. The best results were reported for Ddis=20. In the LN method it is proposed to normalize the value within a window by the mean and standard deviation. Best results were reported for window sizes of 7x7. In the case of the DCT method, we assigned weights to eliminate the coefficients of the low frequency components using a GA. In the case of the LN method for a fixed window size of 7x7, we selected the normalization method by a GA. We compare results of our proposed method to those with no illumination compensation and to those previously published for DCT and LN methods. We use three internationally available face databases Yale B, CMU PIE and FERET where the first two contain face images with significant changes in illumination conditions. We used Yale B for training and CMU PIE and FERET for testing. Our results show significant improvements in face recognition in the testing database. Our method performs similarly or slightly better than DCT or LN methods in images with non-homogeneous illumination and much better than DCT or LN in images with homogeneous illumination.
{"title":"Genetic improvements in illumination compensation by the discrete cosine transform and local normalization for face recognition","authors":"C. Pérez, L. Castillo","doi":"10.1117/12.807330","DOIUrl":"https://doi.org/10.1117/12.807330","url":null,"abstract":"Face detection and recognition depend strongly on illumination conditions. In this paper, we present improvements in two illumination compensation methods for face recognition. Using genetic algorithms (GA) we select parameters of the Discrete Cosine Transform (DCT) and Local Normalization (LN) methods to improve face recognition. In the DCT method all low frequency components within an isosceles triangle, of side Ddis, are eliminated. The best results were reported for Ddis=20. In the LN method it is proposed to normalize the value within a window by the mean and standard deviation. Best results were reported for window sizes of 7x7. In the case of the DCT method, we assigned weights to eliminate the coefficients of the low frequency components using a GA. In the case of the LN method for a fixed window size of 7x7, we selected the normalization method by a GA. We compare results of our proposed method to those with no illumination compensation and to those previously published for DCT and LN methods. We use three internationally available face databases Yale B, CMU PIE and FERET where the first two contain face images with significant changes in illumination conditions. We used Yale B for training and CMU PIE and FERET for testing. Our results show significant improvements in face recognition in the testing database. Our method performs similarly or slightly better than DCT or LN methods in images with non-homogeneous illumination and much better than DCT or LN in images with homogeneous illumination.","PeriodicalId":91154,"journal":{"name":"Optomechatronic Technologies (ISOT), 2010 International Symposium on : 25-27 Oct. 2010 : [Toronto, ON]. International Symposium on Optomechatronic Technologies (2010 : Toronto, Ont.)","volume":"70 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2008-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87363321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：