CarvingNet: Content-Guided Seam Carving Using Deep Convolution Neural Network
We propose an improved content-aware image resizing method that uses deep learning. The proposed method is extended from seam carving, which is another image resizing method. Seam carving uses the energy map from an image. It also removes a seam where the energy is the minimum. We propose a method f...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8565840/ |
| _version_ | 1818874831742959616 |
|---|---|
| author | Eungyeol Song Minkyu Lee Sangyoun Lee |
| author_facet | Eungyeol Song Minkyu Lee Sangyoun Lee |
| author_sort | Eungyeol Song |
| collection | DOAJ |
| description | We propose an improved content-aware image resizing method that uses deep learning. The proposed method is extended from seam carving, which is another image resizing method. Seam carving uses the energy map from an image. It also removes a seam where the energy is the minimum. We propose a method for creating a deep energy map using an encoder–decoder convolution neural network. A deep energy map preserves important parts or boundaries in an image, without distortion. Furthermore, it has the characteristic that uniform intensity of edges is displayed for all images. Four well-known resizing methods and our proposed method were evaluated in terms of aspect ratio similarity. In such an objective evaluation, the proposed method demonstrated better results than the other four algorithms. Our proposed method can reduce the size of an image without damaging the overall structure or losing important information in the image. |
| first_indexed | 2024-12-19T13:16:51Z |
| format | Article |
| id | doaj.art-4f64d682fa3d4482a7193cd7d8764e97 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T13:16:51Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4f64d682fa3d4482a7193cd7d8764e972022-12-21T20:19:48ZengIEEEIEEE Access2169-35362019-01-01728429210.1109/ACCESS.2018.28853478565840CarvingNet: Content-Guided Seam Carving Using Deep Convolution Neural NetworkEungyeol Song0https://orcid.org/0000-0002-5065-2969Minkyu Lee1https://orcid.org/0000-0001-8670-0144Sangyoun Lee2Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South KoreaDepartment of Electrical and Electronic Engineering, Yonsei University, Seoul, South KoreaDepartment of Electrical and Electronic Engineering, Yonsei University, Seoul, South KoreaWe propose an improved content-aware image resizing method that uses deep learning. The proposed method is extended from seam carving, which is another image resizing method. Seam carving uses the energy map from an image. It also removes a seam where the energy is the minimum. We propose a method for creating a deep energy map using an encoder–decoder convolution neural network. A deep energy map preserves important parts or boundaries in an image, without distortion. Furthermore, it has the characteristic that uniform intensity of edges is displayed for all images. Four well-known resizing methods and our proposed method were evaluated in terms of aspect ratio similarity. In such an objective evaluation, the proposed method demonstrated better results than the other four algorithms. Our proposed method can reduce the size of an image without damaging the overall structure or losing important information in the image.https://ieeexplore.ieee.org/document/8565840/Image retargetingseam carvingCNNimage resize |
| spellingShingle | Eungyeol Song Minkyu Lee Sangyoun Lee CarvingNet: Content-Guided Seam Carving Using Deep Convolution Neural Network IEEE Access Image retargeting seam carving CNN image resize |
| title | CarvingNet: Content-Guided Seam Carving Using Deep Convolution Neural Network |
| title_full | CarvingNet: Content-Guided Seam Carving Using Deep Convolution Neural Network |
| title_fullStr | CarvingNet: Content-Guided Seam Carving Using Deep Convolution Neural Network |
| title_full_unstemmed | CarvingNet: Content-Guided Seam Carving Using Deep Convolution Neural Network |
| title_short | CarvingNet: Content-Guided Seam Carving Using Deep Convolution Neural Network |
| title_sort | carvingnet content guided seam carving using deep convolution neural network |
| topic | Image retargeting seam carving CNN image resize |
| url | https://ieeexplore.ieee.org/document/8565840/ |
| work_keys_str_mv | AT eungyeolsong carvingnetcontentguidedseamcarvingusingdeepconvolutionneuralnetwork AT minkyulee carvingnetcontentguidedseamcarvingusingdeepconvolutionneuralnetwork AT sangyounlee carvingnetcontentguidedseamcarvingusingdeepconvolutionneuralnetwork |