In this paper image quality of two types of compression methods, wavelet based and seam carving based are investigated. A metric is introduced to compare the image quality under wavelet and seam carving schemes. Meyer...In this paper image quality of two types of compression methods, wavelet based and seam carving based are investigated. A metric is introduced to compare the image quality under wavelet and seam carving schemes. Meyer, Coiflet 2 and Jpeg2000 wavelet based methods are used as the wavelet based methods. Hausdorf distance based metric (HDM) is proposed and used for the comparison of the two compression methods instead of model based matching techniques and correspondence-based matching techniques, because there is no pairing of points in the two sets being compared. In addition entropy based metric (EM) or peak signal to noise ration based metric (PSNRM) cannot be used to compare the two schemes as the seam carving tends to deform the objects. The wavelet compressed images with different compression percentages were analyzed with HDM and EM and it was observed that HDM follows the EM/PSNRM for wavelet based compression methods. Then HDM is used to compare the wavelet and seam carved images for different compression percentages. The initial results showed that HDM is better metric for comparing wavelet based and seam carved images.展开更多
Straightforward image resizing operators without considering image contents （e.g., uniform scaling） cannot usually produce satisfactory results, while content-aware image retargeting aims to arbitrarily change image...Straightforward image resizing operators without considering image contents （e.g., uniform scaling） cannot usually produce satisfactory results, while content-aware image retargeting aims to arbitrarily change image size while preserving visually prominent features. In this paper, a cluster-based saliency-guided seam carving algorithm for content- aware image retargeting is proposed. To cope with the main drawback of the original seam carving algorithm relying on only gradient-based image importance map, we integrate a gradient-based map and a cluster-based saliency map to generate a more reliable importance map, resulting in better single image retargeting results. Experimental results have demonstrated the efficacy of the proposed algorithm.展开更多
Image resizing is a key technique for displaying images on different devices, and has attracted much attention in the past few years. This paper reviews the image resizing methods proposed in recent years, gives a det...Image resizing is a key technique for displaying images on different devices, and has attracted much attention in the past few years. This paper reviews the image resizing methods proposed in recent years, gives a detailed comparison on their performance, and reveals the main challenges raised in several important issues such as preserving an important region, minimizing distortions, and improving efficiency. Furthermore, this paper discusses the research trends and points out the possible hotspots in this field. We believe this survey can give some guidance for researchers from relevant research areas, offering them an overall and novel view.展开更多
Traditional image resizing methods usually work in pixel space and use various saliency measures.The challenge is to adjust the image shape while trying to preserve important content.In this paper we perform image res...Traditional image resizing methods usually work in pixel space and use various saliency measures.The challenge is to adjust the image shape while trying to preserve important content.In this paper we perform image resizing in feature space using the deep layers of a neural network containing rich important semantic information.We directly adjust the image feature maps,extracted from a pre-trained classification network,and reconstruct the resized image using neuralnetwork based optimization.This novel approach leverages the hierarchical encoding of the network,and in particular,the high-level discriminative power of its deeper layers,that can recognize semantic regions and objects,thereby allowing maintenance of their aspect ratios.Our use of reconstruction from deep features results in less noticeable artifacts than use of imagespace resizing operators.We evaluate our method on benchmarks,compare it to alternative approaches,and demonstrate its strengths on challenging images.展开更多
文摘In this paper image quality of two types of compression methods, wavelet based and seam carving based are investigated. A metric is introduced to compare the image quality under wavelet and seam carving schemes. Meyer, Coiflet 2 and Jpeg2000 wavelet based methods are used as the wavelet based methods. Hausdorf distance based metric (HDM) is proposed and used for the comparison of the two compression methods instead of model based matching techniques and correspondence-based matching techniques, because there is no pairing of points in the two sets being compared. In addition entropy based metric (EM) or peak signal to noise ration based metric (PSNRM) cannot be used to compare the two schemes as the seam carving tends to deform the objects. The wavelet compressed images with different compression percentages were analyzed with HDM and EM and it was observed that HDM follows the EM/PSNRM for wavelet based compression methods. Then HDM is used to compare the wavelet and seam carved images for different compression percentages. The initial results showed that HDM is better metric for comparing wavelet based and seam carved images.
基金supported by“MOST”under Grants No.105-2628-E-224-001-MY3 and No.103-2221-E-224-034-MY2
文摘Straightforward image resizing operators without considering image contents （e.g., uniform scaling） cannot usually produce satisfactory results, while content-aware image retargeting aims to arbitrarily change image size while preserving visually prominent features. In this paper, a cluster-based saliency-guided seam carving algorithm for content- aware image retargeting is proposed. To cope with the main drawback of the original seam carving algorithm relying on only gradient-based image importance map, we integrate a gradient-based map and a cluster-based saliency map to generate a more reliable importance map, resulting in better single image retargeting results. Experimental results have demonstrated the efficacy of the proposed algorithm.
基金Project supported by the National Natural Science Foundation of China(Nos.U1304616,61133009,61272032,61303093,61202154,and 61370174)the National Basic Research Program(973)of China(No.2011CB302203)
文摘Image resizing is a key technique for displaying images on different devices, and has attracted much attention in the past few years. This paper reviews the image resizing methods proposed in recent years, gives a detailed comparison on their performance, and reveals the main challenges raised in several important issues such as preserving an important region, minimizing distortions, and improving efficiency. Furthermore, this paper discusses the research trends and points out the possible hotspots in this field. We believe this survey can give some guidance for researchers from relevant research areas, offering them an overall and novel view.
文摘Traditional image resizing methods usually work in pixel space and use various saliency measures.The challenge is to adjust the image shape while trying to preserve important content.In this paper we perform image resizing in feature space using the deep layers of a neural network containing rich important semantic information.We directly adjust the image feature maps,extracted from a pre-trained classification network,and reconstruct the resized image using neuralnetwork based optimization.This novel approach leverages the hierarchical encoding of the network,and in particular,the high-level discriminative power of its deeper layers,that can recognize semantic regions and objects,thereby allowing maintenance of their aspect ratios.Our use of reconstruction from deep features results in less noticeable artifacts than use of imagespace resizing operators.We evaluate our method on benchmarks,compare it to alternative approaches,and demonstrate its strengths on challenging images.
