Pub Date : 2001-09-26DOI: 10.1109/ICIAP.2001.956977
Hao Wang
This paper describes a connected component (CC)-based approach to automatic text location and segmentation in natural scene images. A multi-group decomposition scheme is used to deal with the complexity of the color background. Connected component extraction is implemented using the block adjacency graph (BAG) algorithm after noise filtering and runlength smearing (RLS) operation. Some heuristic features and priority adaptive segmentation (PAS) of characters are proposed in block candidate verification and grayscale-based recognition. A prototype system is completed and the experimental results prove the effectiveness of the proposed method.
{"title":"Automatic character location and segmentation in color scene images","authors":"Hao Wang","doi":"10.1109/ICIAP.2001.956977","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.956977","url":null,"abstract":"This paper describes a connected component (CC)-based approach to automatic text location and segmentation in natural scene images. A multi-group decomposition scheme is used to deal with the complexity of the color background. Connected component extraction is implemented using the block adjacency graph (BAG) algorithm after noise filtering and runlength smearing (RLS) operation. Some heuristic features and priority adaptive segmentation (PAS) of characters are proposed in block candidate verification and grayscale-based recognition. A prototype system is completed and the experimental results prove the effectiveness of the proposed method.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"212 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121031699","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957028
R. Lanzarotti, P. Campadelli, N. A. Borghese
We describe an algorithm for automatic features detection in 2D color images of human faces. The algorithm proceeds with subsequent refinements. First, it identifies the sub-images containing each feature (eyes, nose and lips). Afterwards, it processes the single features separately by a blend of techniques which use both color and shape information. The method does not require any manual setting or operator intervention.
{"title":"Automatic features detection for overlapping face images on their 3D range models","authors":"R. Lanzarotti, P. Campadelli, N. A. Borghese","doi":"10.1109/ICIAP.2001.957028","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957028","url":null,"abstract":"We describe an algorithm for automatic features detection in 2D color images of human faces. The algorithm proceeds with subsequent refinements. First, it identifies the sub-images containing each feature (eyes, nose and lips). Afterwards, it processes the single features separately by a blend of techniques which use both color and shape information. The method does not require any manual setting or operator intervention.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122937794","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957009
A. Gentile, D. S. Wills
A key design parameter for embedded SIMD architectures is the amount of image data directly mapped to each processing element defined as the pixel-per-processing-element (PPE) ratio. This paper presents a study to determine the effect of different PPE mapping on the performance and efficiency figures of an embedded SIMD architecture. The correlation between problem size, PPE ratio, and processing element architecture are illustrated for a target implementation in 100 nm technology. A case study is illustrated to derive quantitative measures of performance, energy, and area efficiency. For fixed image size, power consumption, and silicon area, a constrained optimization is performed that indicates that a PPE value of 4 yields to the most efficient system configuration. Results indicate that this system is capable of delivering performance in excess of 1 Tops/s at 2.4 W, operating at 200 MHz, with 16384 PE integrated in about 850 mm/sup 2/.
{"title":"Impact of pixel per processor ratio on embedded SIMD architectures","authors":"A. Gentile, D. S. Wills","doi":"10.1109/ICIAP.2001.957009","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957009","url":null,"abstract":"A key design parameter for embedded SIMD architectures is the amount of image data directly mapped to each processing element defined as the pixel-per-processing-element (PPE) ratio. This paper presents a study to determine the effect of different PPE mapping on the performance and efficiency figures of an embedded SIMD architecture. The correlation between problem size, PPE ratio, and processing element architecture are illustrated for a target implementation in 100 nm technology. A case study is illustrated to derive quantitative measures of performance, energy, and area efficiency. For fixed image size, power consumption, and silicon area, a constrained optimization is performed that indicates that a PPE value of 4 yields to the most efficient system configuration. Results indicate that this system is capable of delivering performance in excess of 1 Tops/s at 2.4 W, operating at 200 MHz, with 16384 PE integrated in about 850 mm/sup 2/.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123014292","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957015
Yuehu Liu, H. Emoto, T. Fujii, S. Ozawa
A two dimensional dynamic programming (DP) matching algorithm is presented which is extended from conventional DP matching. In order to represent the color content of color images, a new concept, dominant color matrices is proposed. The retrieving strategy is divided into two phases to improve both speed and accuracy of the proposed retrieval. In the first phase, a group of candidate images, which are similar to the sample image, are produced by using the global color histogram intersection. In the second, dissimilar images in the group of candidate images are deleted by using the two dimensional DP matching algorithm. In addition, the proposed color-content similarity retrieval of images is used on an experimental database consisting of 120 varied color images. Experimental results show the proposed method is effective.
{"title":"A method for content-based similarity retrieval of images using two dimensional DP matching algorithm","authors":"Yuehu Liu, H. Emoto, T. Fujii, S. Ozawa","doi":"10.1109/ICIAP.2001.957015","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957015","url":null,"abstract":"A two dimensional dynamic programming (DP) matching algorithm is presented which is extended from conventional DP matching. In order to represent the color content of color images, a new concept, dominant color matrices is proposed. The retrieving strategy is divided into two phases to improve both speed and accuracy of the proposed retrieval. In the first phase, a group of candidate images, which are similar to the sample image, are produced by using the global color histogram intersection. In the second, dissimilar images in the group of candidate images are deleted by using the two dimensional DP matching algorithm. In addition, the proposed color-content similarity retrieval of images is used on an experimental database consisting of 120 varied color images. Experimental results show the proposed method is effective.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123166587","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957018
David Guillamet, Jordi Vitrià
This paper presents a technique to obtain a discriminant basis set in an unsupervised way. A non-negative matrix factorization (NMF) is applied over a set of color newspapers to obtain a reduced space considering only positive constraints. This method is compared with the well-known principal component analysis (PCA), obtaining promising results in the task of representing independent behaviors of the input data. With this methodology, we are able to find an ordered list of the basis functions, with it being possible to select some of them for a further discriminant task. Moreover the method can also be applied to the task of automatically extracting object classes from a set of objects.
{"title":"Discriminant basis for object classification","authors":"David Guillamet, Jordi Vitrià","doi":"10.1109/ICIAP.2001.957018","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957018","url":null,"abstract":"This paper presents a technique to obtain a discriminant basis set in an unsupervised way. A non-negative matrix factorization (NMF) is applied over a set of color newspapers to obtain a reduced space considering only positive constraints. This method is compared with the well-known principal component analysis (PCA), obtaining promising results in the task of representing independent behaviors of the input data. With this methodology, we are able to find an ordered list of the basis functions, with it being possible to select some of them for a further discriminant task. Moreover the method can also be applied to the task of automatically extracting object classes from a set of objects.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116946660","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957001
S. Nedevschi, T. Mariţa, D. Puiu
An intermediate representation suitable for the 2D recognition of 3D objects, from a single intensity image is proposed. Determination of the intermediate representation from CAD models and from intensity images is presented. This representation uses as primitives line segments and ellipsoidal arcs. A complete technique for fitting contour lines with these primitives has been developed. The method has been proved very accurate and robust to noise, thus it is suited for a variety of applications such as matching and recognition of objects in real-life images.
{"title":"Intermediate representation in model based recognition using straight line and ellipsoidal arc primitives","authors":"S. Nedevschi, T. Mariţa, D. Puiu","doi":"10.1109/ICIAP.2001.957001","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957001","url":null,"abstract":"An intermediate representation suitable for the 2D recognition of 3D objects, from a single intensity image is proposed. Determination of the intermediate representation from CAD models and from intensity images is presented. This representation uses as primitives line segments and ellipsoidal arcs. A complete technique for fitting contour lines with these primitives has been developed. The method has been proved very accurate and robust to noise, thus it is suited for a variety of applications such as matching and recognition of objects in real-life images.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"157 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128807681","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957075
M. P. Yu, K. C. Lo
We propose an heuristic approach to color-quantize images with contextual information taken into consideration. The idea is to locate the regions of an image having the greatest need for colors, and allocate more quantization levels to them. We achieve this by scanning the elements of the input image in a way determined by their local intensity and select the color representatives that comprise the color map according to their local popularity. The overall performance of the color quantization algorithm is evaluated on representative set of artificial and real-world images. The results show a significant image quality improvement compared to some of the other color quantization schemes.
{"title":"Contextual color quantization algorithm","authors":"M. P. Yu, K. C. Lo","doi":"10.1109/ICIAP.2001.957075","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957075","url":null,"abstract":"We propose an heuristic approach to color-quantize images with contextual information taken into consideration. The idea is to locate the regions of an image having the greatest need for colors, and allocate more quantization levels to them. We achieve this by scanning the elements of the input image in a way determined by their local intensity and select the color representatives that comprise the color map according to their local popularity. The overall performance of the color quantization algorithm is evaluated on representative set of artificial and real-world images. The results show a significant image quality improvement compared to some of the other color quantization schemes.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129173891","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957042
R. Pirrone
An original approach to texture-based classification of regions, for image indexing and retrieval, is presented. The system addresses automatic macro-textured ROI detection, and classification: we focus our attention on those objects that can be characterized by a texture as a whole, like trees, flowers, walls, clouds, and so on. The proposed architecture is based on the computation of the /spl lambda/ vector from each selected region, and classification of this feature by means of a pool of suitably trained support vector machines (SVM). This approach is an extension of the one previously developed by some of the authors to classify image regions on the basis of the geometrical shape of the objects they contain. Theoretical remarks, motivation of the approach, experimental setup, and the first satisfactory results on natural scenes are reported.
{"title":"Texture classification for content-based image retrieval","authors":"R. Pirrone","doi":"10.1109/ICIAP.2001.957042","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957042","url":null,"abstract":"An original approach to texture-based classification of regions, for image indexing and retrieval, is presented. The system addresses automatic macro-textured ROI detection, and classification: we focus our attention on those objects that can be characterized by a texture as a whole, like trees, flowers, walls, clouds, and so on. The proposed architecture is based on the computation of the /spl lambda/ vector from each selected region, and classification of this feature by means of a pool of suitably trained support vector machines (SVM). This approach is an extension of the one previously developed by some of the authors to classify image regions on the basis of the geometrical shape of the objects they contain. Theoretical remarks, motivation of the approach, experimental setup, and the first satisfactory results on natural scenes are reported.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116300980","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957051
G. Fumera, F. Roli, G. Vernazza
In the literature, the introduction of the reject option in multiple classifier systems has been analysed only from the experimental point of view. Following a first theoretical analysis provided by the authors, we analyse, within the framework of the minimum risk theory, the problem of finding the best error-reject trade-off achievable by a linear combination of a given set of trained classifiers. An algorithm for computing the parameters of the linear combination and of the reject rule is then proposed. Experimental results on two data sets of remote-sensing images are reported.
{"title":"A method for error rejection in multiple classifier systems","authors":"G. Fumera, F. Roli, G. Vernazza","doi":"10.1109/ICIAP.2001.957051","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957051","url":null,"abstract":"In the literature, the introduction of the reject option in multiple classifier systems has been analysed only from the experimental point of view. Following a first theoretical analysis provided by the authors, we analyse, within the framework of the minimum risk theory, the problem of finding the best error-reject trade-off achievable by a linear combination of a given set of trained classifiers. An algorithm for computing the parameters of the linear combination and of the reject rule is then proposed. Experimental results on two data sets of remote-sensing images are reported.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116203711","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.956994
P. Zingaretti, L. Bossoletti
The paper describes a segmentation technique that well fits to an appearance-based self-localisation. In an appearance-based approach robot positioning is performed without using explicit object models. The choice of the representation of image appearances is fundamental. We use image-domain features, as opposed to interpreted characteristics of the scene, and we adopt feature vectors including both the chromatic attributes of colour sets and their mutual spatial relationships. To obtain the colour sets we perform image segmentation by autothresholding the colour histograms and taking into account what the results are addressed to. The experimental results indicate that the method performs well for a variety of environments.
{"title":"Image segmentation for appearance-based self-localisation","authors":"P. Zingaretti, L. Bossoletti","doi":"10.1109/ICIAP.2001.956994","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.956994","url":null,"abstract":"The paper describes a segmentation technique that well fits to an appearance-based self-localisation. In an appearance-based approach robot positioning is performed without using explicit object models. The choice of the representation of image appearances is fundamental. We use image-domain features, as opposed to interpreted characteristics of the scene, and we adopt feature vectors including both the chromatic attributes of colour sets and their mutual spatial relationships. To obtain the colour sets we perform image segmentation by autothresholding the colour histograms and taking into account what the results are addressed to. The experimental results indicate that the method performs well for a variety of environments.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116419371","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：