Improving the existing face recognition technology to a higher level and to make it useful for many areas of applications including homeland security is a major challenge. Face images are prone to variations that are caused due to expressions, partial occlusions and lighting. These facial variations are responsible for the low accuracy rates of the existing face recognition techniques especially the ones that are based on linear subspace methods. A methodology to improve the accuracies of the face recognition techniques in the presence of facial variations is presented in this paper. An optical-flow method based on 'Lucas and Kanade' technique has been implemented to obtain the flow-field between the neutral face template and the test image to identify the variations. Face recognition is performed on the modularized face images rather than the whole image. A confidence level is associated with each module of the test image based on the measured amount of variation in that module. It is observed that the amount of variations within a module is proportional to the sum of the magnitudes of the optical-flow vectors within those modules. Least confidence is attached to those modules, which has the maximum sum of magnitudes of the optical-flow vectors. A K-nearest neighbor distance measure is implemented to classify each module of the test image individually after projecting it into the corresponding subspace. The confidence associated with each module is taken into consideration to calculate the total score for each training class for the classification of the test image. Analysis of the algorithm is performed with respect to two linear subspaces - PCA and LDA. A high percentage of increase in accuracy is recorded with the implementation of the proposed algorithm on available face databases when compared with other conventional methods
将现有的人脸识别技术提高到更高的水平，并使其在包括国土安全在内的许多领域应用是一个重大的挑战。面部图像容易因表情、部分遮挡和光照而发生变化。这些面部变化导致现有的人脸识别技术准确率较低，尤其是基于线性子空间方法的人脸识别技术。提出了一种在存在面部变化的情况下提高人脸识别技术准确性的方法。采用基于“Lucas and Kanade”技术的光流方法获取中性人脸模板与测试图像之间的流场，从而识别出中性人脸模板与测试图像之间的变化。人脸识别是对模块化的人脸图像进行识别，而不是对整个人脸图像进行识别。一个置信水平与测试图像的每个模块相关联，基于该模块中测量到的变化量。可以观察到，一个模块内的变化量与这些模块内光流矢量的大小之和成正比。最小置信度附加到那些具有最大的光流矢量的大小和的模块。在将测试图像投影到相应的子空间后，实现k近邻距离度量对测试图像的每个模块进行单独分类。考虑与每个模块相关联的置信度来计算每个训练类的总分，用于测试图像的分类。针对PCA和LDA两个线性子空间对该算法进行了分析。与其他传统方法相比，该算法在可用的人脸数据库上实现的准确率提高了很高的百分比
{"title":"Adaptive confidence level assignment to segmented human face regions for improved face recognition","authors":"Satyanadh Gundimada, V. Asari","doi":"10.1109/AIPR.2005.13","DOIUrl":"https://doi.org/10.1109/AIPR.2005.13","url":null,"abstract":"Improving the existing face recognition technology to a higher level and to make it useful for many areas of applications including homeland security is a major challenge. Face images are prone to variations that are caused due to expressions, partial occlusions and lighting. These facial variations are responsible for the low accuracy rates of the existing face recognition techniques especially the ones that are based on linear subspace methods. A methodology to improve the accuracies of the face recognition techniques in the presence of facial variations is presented in this paper. An optical-flow method based on 'Lucas and Kanade' technique has been implemented to obtain the flow-field between the neutral face template and the test image to identify the variations. Face recognition is performed on the modularized face images rather than the whole image. A confidence level is associated with each module of the test image based on the measured amount of variation in that module. It is observed that the amount of variations within a module is proportional to the sum of the magnitudes of the optical-flow vectors within those modules. Least confidence is attached to those modules, which has the maximum sum of magnitudes of the optical-flow vectors. A K-nearest neighbor distance measure is implemented to classify each module of the test image individually after projecting it into the corresponding subspace. The confidence associated with each module is taken into consideration to calculate the total score for each training class for the classification of the test image. Analysis of the algorithm is performed with respect to two linear subspaces - PCA and LDA. A high percentage of increase in accuracy is recorded with the implementation of the proposed algorithm on available face databases when compared with other conventional methods","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114054827","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}
Content-based image retrieval is the task of recalling images from a large database that are similar to a probe image. Many schemes have been proposed and often follow the scheme of extracting information from images and classifying this information as a single entity. We propose that image segments are far more complicated and that two adjustments are necessary. The first is that pixels do not necessarily belong to a single object and the second is that image segments can not be classified as a single entity. We propose a new approach that adopts these tenets and present results indicating the feasibility of creating syntactical definitions to image objects.
{"title":"Content based object retrieval with image primitive database","authors":"J. Kinser, Guisong Wang","doi":"10.1109/AIPR.2005.24","DOIUrl":"https://doi.org/10.1109/AIPR.2005.24","url":null,"abstract":"Content-based image retrieval is the task of recalling images from a large database that are similar to a probe image. Many schemes have been proposed and often follow the scheme of extracting information from images and classifying this information as a single entity. We propose that image segments are far more complicated and that two adjustments are necessary. The first is that pixels do not necessarily belong to a single object and the second is that image segments can not be classified as a single entity. We propose a new approach that adopts these tenets and present results indicating the feasibility of creating syntactical definitions to image objects.","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122432857","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}
Most of the available research on face recognition has been performed using gray scale imagery. This paper presents a novel two-pass face recognition system that uses a multispectral random field texture model, specifically the multispectral simultaneous auto regressive (MSAR) model, and illumination invariant color features. During the first pass, the system detects and segments a face from the background of a color image, and confirms the detection based on a statistically modeled skin pixel map and the elliptical nature of human faces. In the second pass, the face regions are located using the same image segmentation approach on a subspace of the original image, biometric information, and spatial relationships. The determined facial features are then assigned biometric values based on anthropometries, and a set of vectors is created to determine similarity in the facial feature space
{"title":"Face recognition using multispectral random field texture models, color content, and biometric features","authors":"O. Hernandez, Mitchell S. Kleiman","doi":"10.1109/AIPR.2005.28","DOIUrl":"https://doi.org/10.1109/AIPR.2005.28","url":null,"abstract":"Most of the available research on face recognition has been performed using gray scale imagery. This paper presents a novel two-pass face recognition system that uses a multispectral random field texture model, specifically the multispectral simultaneous auto regressive (MSAR) model, and illumination invariant color features. During the first pass, the system detects and segments a face from the background of a color image, and confirms the detection based on a statistically modeled skin pixel map and the elliptical nature of human faces. In the second pass, the face regions are located using the same image segmentation approach on a subspace of the original image, biometric information, and spatial relationships. The determined facial features are then assigned biometric values based on anthropometries, and a set of vectors is created to determine similarity in the facial feature space","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127931334","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}
Conventional RF image formation relies on a fixed waveform set that is based largely on obtaining maximum resolution for a given amount of bandwidth present in a waveform. However, the correlation process for a given waveform set varies widely depending on the cross correlation properties of the waveform and the geometry of the aperture interrogating the object to be imaged. We propose a method that maximizes quality of the imagery being reconstructed based by first using an orthogonal basis to minimize the unwanted correlation response for the waveform. We then shape the frequency and temporal correlation response of the waveform for a given target using a rate distortion criterion and demonstrate the performance of the method
{"title":"A rate distortion method for waveform design in RF image formation","authors":"R. Bonneau","doi":"10.1109/AIPR.2005.11","DOIUrl":"https://doi.org/10.1109/AIPR.2005.11","url":null,"abstract":"Conventional RF image formation relies on a fixed waveform set that is based largely on obtaining maximum resolution for a given amount of bandwidth present in a waveform. However, the correlation process for a given waveform set varies widely depending on the cross correlation properties of the waveform and the geometry of the aperture interrogating the object to be imaged. We propose a method that maximizes quality of the imagery being reconstructed based by first using an orthogonal basis to minimize the unwanted correlation response for the waveform. We then shape the frequency and temporal correlation response of the waveform for a given target using a rate distortion criterion and demonstrate the performance of the method","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115481969","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}
A. Achanta, M. McKenna, J. Heyman, K. Rudd, M. Hinders, Peter J. Costianes
The detection of concealed weapons at a distance is a critical security issue that has been a great challenge for different imaging approaches. In this paper, we discuss the use of ultrasonics in a novel way to probe for metallic and nonmetallic materials under clothing. Conventional ultrasonics has problems penetrating clothing and produces false positives from specular reflections. Our approach is to use ultrasonics to create a localized zone where nonlinear interactions generate a lower frequency acoustic wave that is able to penetrate clothing better than direct ultrasonics. The generation of a probing beam for concealed weapons is described in this brief summary showing comparisons of the physical models with the experimental data. An imaging scan of concealed improvised weapons seized by officials at corrections institutes is presented to highlight the value of this approach
{"title":"Nonlinear acoustic concealed weapons detection","authors":"A. Achanta, M. McKenna, J. Heyman, K. Rudd, M. Hinders, Peter J. Costianes","doi":"10.1109/AIPR.2005.37","DOIUrl":"https://doi.org/10.1109/AIPR.2005.37","url":null,"abstract":"The detection of concealed weapons at a distance is a critical security issue that has been a great challenge for different imaging approaches. In this paper, we discuss the use of ultrasonics in a novel way to probe for metallic and nonmetallic materials under clothing. Conventional ultrasonics has problems penetrating clothing and produces false positives from specular reflections. Our approach is to use ultrasonics to create a localized zone where nonlinear interactions generate a lower frequency acoustic wave that is able to penetrate clothing better than direct ultrasonics. The generation of a probing beam for concealed weapons is described in this brief summary showing comparisons of the physical models with the experimental data. An imaging scan of concealed improvised weapons seized by officials at corrections institutes is presented to highlight the value of this approach","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127897528","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}
In this paper, we propose a novel technique based on maximization of mutual information (MMI) and multiresolution that is capable of automatic registration of multisensor images captured using multiple airborne cameras by utilizing maximization of mutual information, In contrast to conventional methods that extract and employ feature points, MMI-based algorithms utilize the mutual information found between two given images to compute the registration parameters. These, in turn, are then utilized to perform inter and intra sensor registration. Wavelet based techniques are also used in a multiresolution analysis framework yielding a significant increase in computational efficiency for images captured at different resolutions. Our results indicate that the proposed algorithms are very effective in registering infrared images taken at three different wavelengths with a high resolution visual image of a given scene. The techniques form the foundation of a real-time image processing pipeline for automatic geo-rectification, target detection and mapping
{"title":"Automatic registration of multisensor airborne imagery","authors":"Xiaofeng Fan, H. Rhody, E. Saber","doi":"10.1109/AIPR.2005.21","DOIUrl":"https://doi.org/10.1109/AIPR.2005.21","url":null,"abstract":"In this paper, we propose a novel technique based on maximization of mutual information (MMI) and multiresolution that is capable of automatic registration of multisensor images captured using multiple airborne cameras by utilizing maximization of mutual information, In contrast to conventional methods that extract and employ feature points, MMI-based algorithms utilize the mutual information found between two given images to compute the registration parameters. These, in turn, are then utilized to perform inter and intra sensor registration. Wavelet based techniques are also used in a multiresolution analysis framework yielding a significant increase in computational efficiency for images captured at different resolutions. Our results indicate that the proposed algorithms are very effective in registering infrared images taken at three different wavelengths with a high resolution visual image of a given scene. The techniques form the foundation of a real-time image processing pipeline for automatic geo-rectification, target detection and mapping","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"49 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129333127","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}
Automatic target recognition (ATR) is the process of aided or unaided target detection and recognition using data from different sensors. Fusion techniques are used to improve ATR since this reduces system dependence on a single sensor and increases noise tolerance. In this work, ATR is performed on civilian targets which are considered more difficult to classify than military targets. The dataset is provided by the Night Vision & Electronic Sensors Directorate (NVESD) and is collected using the sensor fusion testbed (SFTB) developed by Northrop Grumman Mission Systems. Stationary color and infrared cameras capture images of seven different vehicles at different orientations and distances. Targets include two sedans, two SUVs, two light trucks and a heavy truck. Fusion is performed at the event level and sensor level using temporal and behavior-knowledge-space (BKS) fusion respectively. It is shown that fusion provides better and robust classification compared to classification of individual frames without fusion. The classification experiment shows, on an average, mean classification rates of 65.0%, 70.1% and 77.7% for individual frame classification, temporal fusion and BKS fusion respectively. It is demonstrated that the classification accuracy increases as the level of fusion goes higher. By combining targets into cars, SUVs and light trucks and thereby reducing the number of classes to three, higher mean classification rates of 75.4%, 90.0% and 94.8% were obtained
{"title":"Civilian target detection using hierarchical fusion","authors":"Balasubramanian Lakshminarayanan, H. Qi","doi":"10.1109/AIPR.2005.22","DOIUrl":"https://doi.org/10.1109/AIPR.2005.22","url":null,"abstract":"Automatic target recognition (ATR) is the process of aided or unaided target detection and recognition using data from different sensors. Fusion techniques are used to improve ATR since this reduces system dependence on a single sensor and increases noise tolerance. In this work, ATR is performed on civilian targets which are considered more difficult to classify than military targets. The dataset is provided by the Night Vision & Electronic Sensors Directorate (NVESD) and is collected using the sensor fusion testbed (SFTB) developed by Northrop Grumman Mission Systems. Stationary color and infrared cameras capture images of seven different vehicles at different orientations and distances. Targets include two sedans, two SUVs, two light trucks and a heavy truck. Fusion is performed at the event level and sensor level using temporal and behavior-knowledge-space (BKS) fusion respectively. It is shown that fusion provides better and robust classification compared to classification of individual frames without fusion. The classification experiment shows, on an average, mean classification rates of 65.0%, 70.1% and 77.7% for individual frame classification, temporal fusion and BKS fusion respectively. It is demonstrated that the classification accuracy increases as the level of fusion goes higher. By combining targets into cars, SUVs and light trucks and thereby reducing the number of classes to three, higher mean classification rates of 75.4%, 90.0% and 94.8% were obtained","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134240780","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}
K. Krishnan, P. Fomitchov, Stephen J. Lomnes, M. Kollegal, F. Jansen
A hybrid imaging system capable of combining the spatial resolution of ultrasound with functional sensitivity of fluorescence optical imaging can render the conventionally ill-posed optical image reconstruction more tractable. In this paper, ultrasonic modulation of diffuse photons from an incoherent source in a turbid medium or FluoroSound has been proposed as a mechanism for dual-modality fusion. Theoretical calculations based on a diffusion approximation for tissue depths up to 2cm and reduced scattering coefficients ranging from 5-20/cm have shown show that diffuse photon modulation increases with scattering, decreases with absorption, reaches a minimum when the acoustic focus is located mid-way between the source and the detector; and can be optimized by a suitably shaped and sized acoustic focus. The diffuse photon modulation signature could potentially be used for improving spatial resolution of deep tissue fluorescence imaging and enable fusion of ultrasound and optical imaging in a single measurement
{"title":"Dual-modality imager based on ultrasonic modulation of incoherent light in turbid medium","authors":"K. Krishnan, P. Fomitchov, Stephen J. Lomnes, M. Kollegal, F. Jansen","doi":"10.1109/AIPR.2005.27","DOIUrl":"https://doi.org/10.1109/AIPR.2005.27","url":null,"abstract":"A hybrid imaging system capable of combining the spatial resolution of ultrasound with functional sensitivity of fluorescence optical imaging can render the conventionally ill-posed optical image reconstruction more tractable. In this paper, ultrasonic modulation of diffuse photons from an incoherent source in a turbid medium or FluoroSound has been proposed as a mechanism for dual-modality fusion. Theoretical calculations based on a diffusion approximation for tissue depths up to 2cm and reduced scattering coefficients ranging from 5-20/cm have shown show that diffuse photon modulation increases with scattering, decreases with absorption, reaches a minimum when the acoustic focus is located mid-way between the source and the detector; and can be optimized by a suitably shaped and sized acoustic focus. The diffuse photon modulation signature could potentially be used for improving spatial resolution of deep tissue fluorescence imaging and enable fusion of ultrasound and optical imaging in a single measurement","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129467274","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}
Correlative interferometry has been proposed for terahertz imaging in applications such as standoff detection of concealed explosives. It offers the advantage of low cost image reconstruction in the pupil plane given the current unavailability of ready-to-use focal plane imaging technology at these wavelengths. Current interferometric approaches are based on finding the inverse Fourier transform of the spatial correlation computed from field measurements at a distance. This paper proposes an image reconstruction approach that provides a constrained least squares fit between computed autocorrelation from sensor measurements and the expression for the far field autocorrelation for extended objects and line arrays
{"title":"Constrained optimal interferometric imaging of extended objects","authors":"R. Rao, B. Himed","doi":"10.1109/AIPR.2005.23","DOIUrl":"https://doi.org/10.1109/AIPR.2005.23","url":null,"abstract":"Correlative interferometry has been proposed for terahertz imaging in applications such as standoff detection of concealed explosives. It offers the advantage of low cost image reconstruction in the pupil plane given the current unavailability of ready-to-use focal plane imaging technology at these wavelengths. Current interferometric approaches are based on finding the inverse Fourier transform of the spatial correlation computed from field measurements at a distance. This paper proposes an image reconstruction approach that provides a constrained least squares fit between computed autocorrelation from sensor measurements and the expression for the far field autocorrelation for extended objects and line arrays","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132979086","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}
Man from the beginning of time, tried to automate things for comfort, accuracy, precision and speed. Technology advanced from manual to mechanical and then from mechanical to automatic. Vision based applications are the products of the future. Machine vision systems integrate electronic components with software systems to imitate a variety of human functions. This paper describes current research on a vision based inspection system. A computer using a camera as an eye has replaced the manual inspection system. The camera is mounted on a conveyor belt. The main objective is to inspect for defects, instead of using complicated filters like edge enhancement, and correlation etc. a very simple technique has been implemented. Since the objects are moving over the conveyor belt so time is a factor that should be counted for. Using filters or correlation procedures give better results but consume a lot of time. The technique discussed in this paper inspects on the basic pixel level. It checks on the basis of size, shape, color and dimensions. We have implemented it on five applications and the results achieved were good enough to prove that the algorithm works as desired
{"title":"Automatic inspection system using machine vision","authors":"U. S. Khan, J. Iqbal, Mahmood A. Khan","doi":"10.1109/AIPR.2005.20","DOIUrl":"https://doi.org/10.1109/AIPR.2005.20","url":null,"abstract":"Man from the beginning of time, tried to automate things for comfort, accuracy, precision and speed. Technology advanced from manual to mechanical and then from mechanical to automatic. Vision based applications are the products of the future. Machine vision systems integrate electronic components with software systems to imitate a variety of human functions. This paper describes current research on a vision based inspection system. A computer using a camera as an eye has replaced the manual inspection system. The camera is mounted on a conveyor belt. The main objective is to inspect for defects, instead of using complicated filters like edge enhancement, and correlation etc. a very simple technique has been implemented. Since the objects are moving over the conveyor belt so time is a factor that should be counted for. Using filters or correlation procedures give better results but consume a lot of time. The technique discussed in this paper inspects on the basic pixel level. It checks on the basis of size, shape, color and dimensions. We have implemented it on five applications and the results achieved were good enough to prove that the algorithm works as desired","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116074023","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：