Traditional image compression algorithms treat all image regions equally, regardless of their content, often resulting in reconstructed images that do not correlate well with human perception. Content-aware compression, on the other hand, prioritizes image regions that are more relevant to the interpretation of an image and encodes them at a higher bitrate, i.e. without loss or with less loss, than the rest of the image. Our paper explores the multi-structure region of interest (MS-ROI) model, a convolutional neural network, which enables the localization of multiple regions of interest (ROIs) in an image. The localization is expressed as a corresponding saliency map, which identifies the relevance of individual image regions and provides a saliency value for each pixel of the given image. This information is then used to guide the compression. The saliency values are discretized into multiple levels and more important levels are encoded with a higher quality factor Q than the less important ones, allowing for most of the reduction in image resolution to occur in non-salient image regions. Because the generated saliency maps produce soft boundaries between salient and non-salient image regions, smooth transitions between these regions are achieved. The obtained image is then encoded further using the standard JPEG algorithm with a uniform Q factor, resulting in the final image of the standard JPEG format. Our model was trained on the Caltech-101 image dataset and its performance was tested on two other image datasets. Presented are the obtained saliency maps for several images, as well as the results of contentaware compression, which are compared to the standard JPEG compression at different Q factors. For an objective comparison and evaluation of the quality of the obtained images, various standard quality metrics were used, i.e. mean squared error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM) and multi-scale structural similarity index (MS-SSIM).
{"title":"CONTENT-AWARE IMAGE COMPRESSION WITH CONVOLUTIONAL NEURAL NETWORKS","authors":"Alen Selimović, A. Hladnik","doi":"10.24867/GRID-2018-P56","DOIUrl":"https://doi.org/10.24867/GRID-2018-P56","url":null,"abstract":"Traditional image compression algorithms treat all image regions equally, regardless of their content, often resulting in reconstructed images that do not correlate well with human perception. Content-aware compression, on the other hand, prioritizes image regions that are more relevant to the interpretation of an image and encodes them at a higher bitrate, i.e. without loss or with less loss, than the rest of the image. Our paper explores the multi-structure region of interest (MS-ROI) model, a convolutional neural network, which enables the localization of multiple regions of interest (ROIs) in an image. The localization is expressed as a corresponding saliency map, which identifies the relevance of individual image regions and provides a saliency value for each pixel of the given image. This information is then used to guide the compression. The saliency values are discretized into multiple levels and more important levels are encoded with a higher quality factor Q than the less important ones, allowing for most of the reduction in image resolution to occur in non-salient image regions. Because the generated saliency maps produce soft boundaries between salient and non-salient image regions, smooth transitions between these regions are achieved. The obtained image is then encoded further using the standard JPEG algorithm with a uniform Q factor, resulting in the final image of the standard JPEG format. Our model was trained on the Caltech-101 image dataset and its performance was tested on two other image datasets. Presented are the obtained saliency maps for several images, as well as the results of contentaware compression, which are compared to the standard JPEG compression at different Q factors. For an objective comparison and evaluation of the quality of the obtained images, various standard quality metrics were used, i.e. mean squared error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM) and multi-scale structural similarity index (MS-SSIM).","PeriodicalId":371126,"journal":{"name":"Proceedings of 9th International Symposium on Graphic Engineering and Design","volume":"72 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":"121191811","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}
Josip Bota, Sonja Jamnicki Hanzer, D. Banić, M. Brozović
Rectangles are the most common packaging shapes. Their stability under compression can vary according to different types of paperboard as well as panels ratios. Rectangular shapes have advantages in transportation and production but are not the only shapes that paperboard packaging has to offer. This paper investigates seven packaging shapes with different cross-sections while keeping the same height and amount of material used. The tested shapes were made with two types of paperboard (with recycled fibre and virgin pulp) and different grammage. The testing was conducted using a modified Crush Test (Lorentzen & Wettre Crush Tester). The results showed that cylinder shape has the most compression resistance while triangular prism and rectangular prism (1:4 panel ratio) the least. Testing rectangles with different panel ratios together with the results of other shapes led to the conclusion that compression resistance mainly depends on the size of the panel. If a shape has larger (less number of) panels it has less resistance to vertical pressure (stackability).
{"title":"COMPRESSION RESISTANCE OF SMALL PAPERBOARD PACKAGING SHAPES","authors":"Josip Bota, Sonja Jamnicki Hanzer, D. Banić, M. Brozović","doi":"10.24867/GRID-2018-P29","DOIUrl":"https://doi.org/10.24867/GRID-2018-P29","url":null,"abstract":"Rectangles are the most common packaging shapes. Their stability under compression can vary according to different types of paperboard as well as panels ratios. Rectangular shapes have advantages in transportation and production but are not the only shapes that paperboard packaging has to offer. This paper investigates seven packaging shapes with different cross-sections while keeping the same height and amount of material used. The tested shapes were made with two types of paperboard (with recycled fibre and virgin pulp) and different grammage. The testing was conducted using a modified Crush Test (Lorentzen & Wettre Crush Tester). The results showed that cylinder shape has the most compression resistance while triangular prism and rectangular prism (1:4 panel ratio) the least. Testing rectangles with different panel ratios together with the results of other shapes led to the conclusion that compression resistance mainly depends on the size of the panel. If a shape has larger (less number of) panels it has less resistance to vertical pressure (stackability).","PeriodicalId":371126,"journal":{"name":"Proceedings of 9th International Symposium on Graphic Engineering and Design","volume":"10 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":"127729971","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：