Pub Date : 2018-11-01DOI: 10.1109/IPTA.2018.8608167
Yufang Bao, H. Krim
In this paper, we propose a cohort of new methods that cooperate together to improve the detection/tracking of mosquitos in a 2D video clip. A commonly recognized challenge in the biotechnology research field is evaluating the effect of a repellent which entails tracking the unpredictable flight paths of the insects, which may be swift flying or slow moving. Our work presented in this paper provides an efficient tool to deal with tracking the small insects with unpredictable moving patterns by proposing a new dual foreground and background modeling/updating system for target detecting and tracking. The proposed processing elements take advantage of the similarity of the frames and use the estimated speeds to collectively capture the relevant information and contribute in concert to ensure fast and accurate measurement to reach the goal of behavior evaluation of mosquitos in response to a repellent.
{"title":"Video Tracking of Insect Flight Path: Towards Behavioral Assessment","authors":"Yufang Bao, H. Krim","doi":"10.1109/IPTA.2018.8608167","DOIUrl":"https://doi.org/10.1109/IPTA.2018.8608167","url":null,"abstract":"In this paper, we propose a cohort of new methods that cooperate together to improve the detection/tracking of mosquitos in a 2D video clip. A commonly recognized challenge in the biotechnology research field is evaluating the effect of a repellent which entails tracking the unpredictable flight paths of the insects, which may be swift flying or slow moving. Our work presented in this paper provides an efficient tool to deal with tracking the small insects with unpredictable moving patterns by proposing a new dual foreground and background modeling/updating system for target detecting and tracking. The proposed processing elements take advantage of the similarity of the frames and use the estimated speeds to collectively capture the relevant information and contribute in concert to ensure fast and accurate measurement to reach the goal of behavior evaluation of mosquitos in response to a repellent.","PeriodicalId":272294,"journal":{"name":"2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114662780","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}
Pub Date : 2018-11-01DOI: 10.1109/IPTA.2018.8608128
Dongfeng Mei, Xuan Zhu, Cheng Yue, Qingwen Cao, Lei Wang, Longfei Zhang, Q. Song
Image super-resolution based on learning dictionary has recently attracted enormous interests. The learning-based methods usually train a pair of dictionaries from low-resolution and high-resolution image patches, ignoring the fact that patches have different structures. In this paper, we propose to train a set of novel multi-pairs of dictionaries for different categories of patches which clustered by gaussian mixture model, instead of a global dictionary trained from all patches. The multi-pairs of dictionaries via patch prior guided clustering can express structure information of the image patches well. Extensive experimental results prove it has strong robustness in super resolution. Compared with state-of-the-art SR methods, our method demonstrates more pleasant quality of image edge structures and texture.
{"title":"Image Super-Resolution based on multi-pairs of dictionaries via Patch Prior Guided Clustering","authors":"Dongfeng Mei, Xuan Zhu, Cheng Yue, Qingwen Cao, Lei Wang, Longfei Zhang, Q. Song","doi":"10.1109/IPTA.2018.8608128","DOIUrl":"https://doi.org/10.1109/IPTA.2018.8608128","url":null,"abstract":"Image super-resolution based on learning dictionary has recently attracted enormous interests. The learning-based methods usually train a pair of dictionaries from low-resolution and high-resolution image patches, ignoring the fact that patches have different structures. In this paper, we propose to train a set of novel multi-pairs of dictionaries for different categories of patches which clustered by gaussian mixture model, instead of a global dictionary trained from all patches. The multi-pairs of dictionaries via patch prior guided clustering can express structure information of the image patches well. Extensive experimental results prove it has strong robustness in super resolution. Compared with state-of-the-art SR methods, our method demonstrates more pleasant quality of image edge structures and texture.","PeriodicalId":272294,"journal":{"name":"2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121091383","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}
Pub Date : 2018-11-01DOI: 10.1109/IPTA.2018.8608122
V. Itier, Florentin Kucharczak, O. Strauss, W. Puech
JPEG is the most used image compression algorithm but block wise DCT compression methods produce artifacts due to coefficient quantization. JPEG decompression can be seen as a reconstruction problem constrained by quantization. In this context, we propose to handle this problem by using interval-valued arithmetic. Our method allows to produce interval-valued image that includes the non-compressed original image. The produced convex set allows to apply constrained Total Variation (TV) reconstruction in order to reduce JPEG artifacts (blocking, grainy effects and high frequency noise). Experiments show visual improvement of JPEG decoding assessed by non-reference quality metric. In addition, the stopping criterion of the TV algorithm is given by this metric which provides evidence about JPEG decompression improvement.
{"title":"Interval-valued JPEG decompression for artifact suppression","authors":"V. Itier, Florentin Kucharczak, O. Strauss, W. Puech","doi":"10.1109/IPTA.2018.8608122","DOIUrl":"https://doi.org/10.1109/IPTA.2018.8608122","url":null,"abstract":"JPEG is the most used image compression algorithm but block wise DCT compression methods produce artifacts due to coefficient quantization. JPEG decompression can be seen as a reconstruction problem constrained by quantization. In this context, we propose to handle this problem by using interval-valued arithmetic. Our method allows to produce interval-valued image that includes the non-compressed original image. The produced convex set allows to apply constrained Total Variation (TV) reconstruction in order to reduce JPEG artifacts (blocking, grainy effects and high frequency noise). Experiments show visual improvement of JPEG decoding assessed by non-reference quality metric. In addition, the stopping criterion of the TV algorithm is given by this metric which provides evidence about JPEG decompression improvement.","PeriodicalId":272294,"journal":{"name":"2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"1198 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127235875","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}
Pub Date : 2018-11-01DOI: 10.1109/IPTA.2018.8608129
Jierui Zha, P. Decazes, Jérôme Lapuyade, A. Elmoataz, S. Ruan
In this paper we present a lymphoma detection method on image PET-CT by combining supervoxel and conditional random fields(CRFs). Positron-emission tomography(PET) is often used to analysis diseases like cancer. And it is usually combined with computed tomography scan (CT), which provides accurate anatomical location of lesions. Most lymphoma detection in PET are based on machine learning technique which requires a large learning database. However, it is difficult to acquire such a large standard database in medical field. In our previous work, a new approach which combines an anatomical atlas obtained in CT with CRFs (Conditional Random Fields) in PET is proposed and is proved to have good results, however it is very time consuming due to the fully connection of each voxel in 3D. To cope with this problem, we proposed a method that combines supervoxel and CRFs to accelerate the progress. Our method consists of 3 steps. First, we apply the supervoxel on the PET image to group the voxels into supervoxels. Then, an anatomic atlas is applied on CT to remove the organs having hyper-fixation in PET. Finally, CRFs will detect lymphoma regions in PET. The obtained results show good performance in terms of speed and lymphoma detection.
{"title":"3D lymphoma detection in PET-CT images with supervoxel and CRFs","authors":"Jierui Zha, P. Decazes, Jérôme Lapuyade, A. Elmoataz, S. Ruan","doi":"10.1109/IPTA.2018.8608129","DOIUrl":"https://doi.org/10.1109/IPTA.2018.8608129","url":null,"abstract":"In this paper we present a lymphoma detection method on image PET-CT by combining supervoxel and conditional random fields(CRFs). Positron-emission tomography(PET) is often used to analysis diseases like cancer. And it is usually combined with computed tomography scan (CT), which provides accurate anatomical location of lesions. Most lymphoma detection in PET are based on machine learning technique which requires a large learning database. However, it is difficult to acquire such a large standard database in medical field. In our previous work, a new approach which combines an anatomical atlas obtained in CT with CRFs (Conditional Random Fields) in PET is proposed and is proved to have good results, however it is very time consuming due to the fully connection of each voxel in 3D. To cope with this problem, we proposed a method that combines supervoxel and CRFs to accelerate the progress. Our method consists of 3 steps. First, we apply the supervoxel on the PET image to group the voxels into supervoxels. Then, an anatomic atlas is applied on CT to remove the organs having hyper-fixation in PET. Finally, CRFs will detect lymphoma regions in PET. The obtained results show good performance in terms of speed and lymphoma detection.","PeriodicalId":272294,"journal":{"name":"2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127262445","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}
Pub Date : 2018-11-01DOI: 10.1109/IPTA.2018.8608124
Zheng Hui, Quan Zhou
Block truncation coding (BTC), known as a simple and efficient digital image compression algorithm, its essential is to encode the non-overlapping sub-blocks of input images with a pair of low-/high- quantity levels and a distribution matrix. Absolute Moment Block Truncation Coding (AMBTC) is a widely used modified version of BTC. Based on BTC, we paper propose a new approach by means of an adjusted threshold to classify each sub-block. Then, for those blocks grouped as to be modified we apply a new BTC-based modification method by searching optimized threshold as the replacement of the mean value of sub-blocks in AMBTC for pixels grouping. Experimental results show that, compared with AMBTC, the reconstructed image quality of proposed scheme can be improved by 0.5~0.8dB in Peak signal to noise ratio (PSNR)
{"title":"An Image Compression Scheme Based on Block Truncation Coding Using Real-time Block Classification and Modified Threshold for Pixels Grouping","authors":"Zheng Hui, Quan Zhou","doi":"10.1109/IPTA.2018.8608124","DOIUrl":"https://doi.org/10.1109/IPTA.2018.8608124","url":null,"abstract":"Block truncation coding (BTC), known as a simple and efficient digital image compression algorithm, its essential is to encode the non-overlapping sub-blocks of input images with a pair of low-/high- quantity levels and a distribution matrix. Absolute Moment Block Truncation Coding (AMBTC) is a widely used modified version of BTC. Based on BTC, we paper propose a new approach by means of an adjusted threshold to classify each sub-block. Then, for those blocks grouped as to be modified we apply a new BTC-based modification method by searching optimized threshold as the replacement of the mean value of sub-blocks in AMBTC for pixels grouping. Experimental results show that, compared with AMBTC, the reconstructed image quality of proposed scheme can be improved by 0.5~0.8dB in Peak signal to noise ratio (PSNR)","PeriodicalId":272294,"journal":{"name":"2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129125836","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}
Pub Date : 2018-11-01DOI: 10.1109/IPTA.2018.8608156
Alexandr Yu. Kondrati'ev, H. Yaginuma, Y. Okada, D. Sorokin
The automated segmentation and tracking of cells in live cell microscopy image sequences is an actual problem in many biological research areas. Despite the existence of different cell tracking approaches, a universal solution for this problem still does not exist due to high variety of fluorescent microscopy image data obtained using different techniques, where cells have completely different visual appearance. Moreover, the cells can significantly change their shape even within a single image sequence. In this work, we propose a cell tracking algorithm designed for detecting and tracking cell nuclei in 2D image sequences obtained by epifluorescence microscopy, where the cell appearance drastically changes during cell mitosis. We used marker controlled watershed algorithm combined with blob detection for nuclei segmentation followed by a generalized nearest neighbor approach for nuclei tracking. We also employed a special mitosis detection algorithm to process cell division events. Our approach was quantitatively evaluated for its segmentation and tracking accuracy using the real image data annotated by human experts. The evaluation procedure was performed based on the protocol used in the Cell Tracking Challenge. It was shown that the proposed approach outperforms an existing semiautomatic method in both segmentation and tracking accuracy.
{"title":"A Method for Automatic Tracking of Cell Nuclei in 2D Epifluorescence Microscopy Image Sequences","authors":"Alexandr Yu. Kondrati'ev, H. Yaginuma, Y. Okada, D. Sorokin","doi":"10.1109/IPTA.2018.8608156","DOIUrl":"https://doi.org/10.1109/IPTA.2018.8608156","url":null,"abstract":"The automated segmentation and tracking of cells in live cell microscopy image sequences is an actual problem in many biological research areas. Despite the existence of different cell tracking approaches, a universal solution for this problem still does not exist due to high variety of fluorescent microscopy image data obtained using different techniques, where cells have completely different visual appearance. Moreover, the cells can significantly change their shape even within a single image sequence. In this work, we propose a cell tracking algorithm designed for detecting and tracking cell nuclei in 2D image sequences obtained by epifluorescence microscopy, where the cell appearance drastically changes during cell mitosis. We used marker controlled watershed algorithm combined with blob detection for nuclei segmentation followed by a generalized nearest neighbor approach for nuclei tracking. We also employed a special mitosis detection algorithm to process cell division events. Our approach was quantitatively evaluated for its segmentation and tracking accuracy using the real image data annotated by human experts. The evaluation procedure was performed based on the protocol used in the Cell Tracking Challenge. It was shown that the proposed approach outperforms an existing semiautomatic method in both segmentation and tracking accuracy.","PeriodicalId":272294,"journal":{"name":"2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132556765","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}
Pub Date : 2018-11-01DOI: 10.1109/ipta.2018.8608135
{"title":"[Copyright notice]","authors":"","doi":"10.1109/ipta.2018.8608135","DOIUrl":"https://doi.org/10.1109/ipta.2018.8608135","url":null,"abstract":"","PeriodicalId":272294,"journal":{"name":"2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"350 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134408636","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}
Pub Date : 2018-11-01DOI: 10.1109/IPTA.2018.8608125
A. M. Obeso, J. Benois-Pineau, Kamel Guissous, V. Gouet-Brunet, M. García-Vázquez, A. A. Ramírez-Acosta
Incorporating Human Visual System (HVS) models into building of classifiers has become an intensively researched field in visual content mining. In the variety of models of HVS we are interested in so-called visual saliency maps. Contrarily to scan-paths they model instantaneous attention assigning the degree of interestingness/saliency for humans to each pixel in the image plane. In various tasks of visual content understanding, these maps proved to be efficient stressing contribution of the areas of interest in image plane to classifiers models. In previous works saliency layers have been introduced in Deep CNNs, showing that they allow reducing training time getting similar accuracy and loss values in optimal models. In case of large image collections efficient building of saliency maps is based on predictive models of visual attention. They are generally bottom-up and are not adapted to specific visual tasks. Unless they are built for specific content, such as "urban images"-targeted saliency maps we also compare in this paper. In present research we propose a "bootstrap" strategy of building visual saliency maps for particular tasks of visual data mining. A small collection of images relevant to the visual understanding problem is annotated with gaze fixations. Then the propagation to a large training dataset is ensured and compared with the classical GBVS model and a recent method of saliency for urban image content. The classification results within Deep CNN framework are promising compared to the purely automatic visual saliency prediction.
{"title":"Comparative study of visual saliency maps in the problem of classification of architectural images with Deep CNNs","authors":"A. M. Obeso, J. Benois-Pineau, Kamel Guissous, V. Gouet-Brunet, M. García-Vázquez, A. A. Ramírez-Acosta","doi":"10.1109/IPTA.2018.8608125","DOIUrl":"https://doi.org/10.1109/IPTA.2018.8608125","url":null,"abstract":"Incorporating Human Visual System (HVS) models into building of classifiers has become an intensively researched field in visual content mining. In the variety of models of HVS we are interested in so-called visual saliency maps. Contrarily to scan-paths they model instantaneous attention assigning the degree of interestingness/saliency for humans to each pixel in the image plane. In various tasks of visual content understanding, these maps proved to be efficient stressing contribution of the areas of interest in image plane to classifiers models. In previous works saliency layers have been introduced in Deep CNNs, showing that they allow reducing training time getting similar accuracy and loss values in optimal models. In case of large image collections efficient building of saliency maps is based on predictive models of visual attention. They are generally bottom-up and are not adapted to specific visual tasks. Unless they are built for specific content, such as \"urban images\"-targeted saliency maps we also compare in this paper. In present research we propose a \"bootstrap\" strategy of building visual saliency maps for particular tasks of visual data mining. A small collection of images relevant to the visual understanding problem is annotated with gaze fixations. Then the propagation to a large training dataset is ensured and compared with the classical GBVS model and a recent method of saliency for urban image content. The classification results within Deep CNN framework are promising compared to the purely automatic visual saliency prediction.","PeriodicalId":272294,"journal":{"name":"2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129402091","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 novel enhancement algorithm is presented to solve the problem of over exposure in bright areas of Low illumination image enhancement algorithm. In this paper, a model is proposed which can make the bright region gain compressed, and a complementary map can be generated which contains the bright region information. And a segmentation method is proposed to detect the bright region of the low illumination image. Meanwhile, in order to avoid colour distortion, a brightness transfer fusion strategy is used to the bright area of low illumination images. Experiments have shown that the new algorithm has higher average gradient, higher information entropy and close structural similarity to the original algorithm. So it can get better performance in dealing with the bright region of low illumination images both in subjective and objective.
{"title":"A new enhancement algorithm for the low illumination image based on fog-degraded model","authors":"Feiyan Cheng, Junsheng Shi, Lijun Yun, Zhenhua Du, Zhijian Xu, Xiaoqiao Huang, Zaiqing Chen","doi":"10.1109/IPTA.2018.8608164","DOIUrl":"https://doi.org/10.1109/IPTA.2018.8608164","url":null,"abstract":"A novel enhancement algorithm is presented to solve the problem of over exposure in bright areas of Low illumination image enhancement algorithm. In this paper, a model is proposed which can make the bright region gain compressed, and a complementary map can be generated which contains the bright region information. And a segmentation method is proposed to detect the bright region of the low illumination image. Meanwhile, in order to avoid colour distortion, a brightness transfer fusion strategy is used to the bright area of low illumination images. Experiments have shown that the new algorithm has higher average gradient, higher information entropy and close structural similarity to the original algorithm. So it can get better performance in dealing with the bright region of low illumination images both in subjective and objective.","PeriodicalId":272294,"journal":{"name":"2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128840691","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}
Pub Date : 2018-11-01DOI: 10.1109/IPTA.2018.8608151
Weiyi Wei, Chengfeng A, Yufei Zhao, Guicang Zhang
In the current image registration technology, feature points detection and matching feature points have lower accuracy. Based on the analysis of SURF feature point detection and information entropy for image registration, an image registration algorithm based on SURF feature points is proposed. Firstly, the image is divided into super-pixels, and the information entropy of each image area is calculated. The redundant points in feature points are eliminated by using the value of information quantity. The problem that the SURF operator distributes densely is improved and the number of feature points is reduced. Experimental results show that the improved algorithm can improve the accuracy of image feature point pairs, and effectively improve the quality of registration.
{"title":"Image Registration Algorithm Based on Super pixel Segmentation and SURF Feature Points","authors":"Weiyi Wei, Chengfeng A, Yufei Zhao, Guicang Zhang","doi":"10.1109/IPTA.2018.8608151","DOIUrl":"https://doi.org/10.1109/IPTA.2018.8608151","url":null,"abstract":"In the current image registration technology, feature points detection and matching feature points have lower accuracy. Based on the analysis of SURF feature point detection and information entropy for image registration, an image registration algorithm based on SURF feature points is proposed. Firstly, the image is divided into super-pixels, and the information entropy of each image area is calculated. The redundant points in feature points are eliminated by using the value of information quantity. The problem that the SURF operator distributes densely is improved and the number of feature points is reduced. Experimental results show that the improved algorithm can improve the accuracy of image feature point pairs, and effectively improve the quality of registration.","PeriodicalId":272294,"journal":{"name":"2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114727704","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：