STAug: Copy-Paste Based Image Augmentation Technique Using Salient Target
High-quality, large-capacity data are essential for training a deep learning vision model. However, to construct crop image data, absolute growth time is required for crop growth. In addition, it is characterized by unbalanced data, with fewer abnormal data than normal data. Therefore, building high...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9961191/ |
| _version_ | 1811214082896822272 |
|---|---|
| author | Ji-Soo Kang Kyungyong Chung |
| author_facet | Ji-Soo Kang Kyungyong Chung |
| author_sort | Ji-Soo Kang |
| collection | DOAJ |
| description | High-quality, large-capacity data are essential for training a deep learning vision model. However, to construct crop image data, absolute growth time is required for crop growth. In addition, it is characterized by unbalanced data, with fewer abnormal data than normal data. Therefore, building high-quality, large-scale datasets is challenging. Many studies have used data augmentation of plant images to solve this problem. However, plants require data augmentation that does not compromise their color, texture, or shape. This study proposes the use of salient target augmentation (STAug) as a data augmentation technique to protect the colors and shapes of plant images. The proposed method pastes one image’s salient target into a different image to mix the two images. It uses a salient object detection model to generate a salient object mask of the plant. Using the generated mask, a salient target was identified and cropped in a plant image, and the cropped image data were pasted to different background data for augmentation. Concat mask, a combination of each image’s salient object mask, was designed to create the label of the generated image. It is possible to create a rigid classification model by augmenting the data without damaging the plant features. To verify the performance of the proposed STAug, we compared its performance with that of other data-augmentation policies. When STAug and other augmentation techniques were applied in combination, an accuracy of 0.9733 was achieved. We demonstrated a better classification performance than when it was not applied. |
| first_indexed | 2024-04-12T05:57:04Z |
| format | Article |
| id | doaj.art-4d6c955f670e4f8b84f9b33183d2846e |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T05:57:04Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4d6c955f670e4f8b84f9b33183d2846e2022-12-22T03:45:07ZengIEEEIEEE Access2169-35362022-01-011012360512361310.1109/ACCESS.2022.32241419961191STAug: Copy-Paste Based Image Augmentation Technique Using Salient TargetJi-Soo Kang0https://orcid.org/0000-0003-3433-0094Kyungyong Chung1https://orcid.org/0000-0002-6439-9992Department of Computer Science, Kyonggi University, Suwon-si, South KoreaDivision of AI Computer Science and Engineering, Kyonggi University, Suwon-si, South KoreaHigh-quality, large-capacity data are essential for training a deep learning vision model. However, to construct crop image data, absolute growth time is required for crop growth. In addition, it is characterized by unbalanced data, with fewer abnormal data than normal data. Therefore, building high-quality, large-scale datasets is challenging. Many studies have used data augmentation of plant images to solve this problem. However, plants require data augmentation that does not compromise their color, texture, or shape. This study proposes the use of salient target augmentation (STAug) as a data augmentation technique to protect the colors and shapes of plant images. The proposed method pastes one image’s salient target into a different image to mix the two images. It uses a salient object detection model to generate a salient object mask of the plant. Using the generated mask, a salient target was identified and cropped in a plant image, and the cropped image data were pasted to different background data for augmentation. Concat mask, a combination of each image’s salient object mask, was designed to create the label of the generated image. It is possible to create a rigid classification model by augmenting the data without damaging the plant features. To verify the performance of the proposed STAug, we compared its performance with that of other data-augmentation policies. When STAug and other augmentation techniques were applied in combination, an accuracy of 0.9733 was achieved. We demonstrated a better classification performance than when it was not applied.https://ieeexplore.ieee.org/document/9961191/Copy-pasteimage augmentationplant disease classifiersalient object detection |
| spellingShingle | Ji-Soo Kang Kyungyong Chung STAug: Copy-Paste Based Image Augmentation Technique Using Salient Target IEEE Access Copy-paste image augmentation plant disease classifier salient object detection |
| title | STAug: Copy-Paste Based Image Augmentation Technique Using Salient Target |
| title_full | STAug: Copy-Paste Based Image Augmentation Technique Using Salient Target |
| title_fullStr | STAug: Copy-Paste Based Image Augmentation Technique Using Salient Target |
| title_full_unstemmed | STAug: Copy-Paste Based Image Augmentation Technique Using Salient Target |
| title_short | STAug: Copy-Paste Based Image Augmentation Technique Using Salient Target |
| title_sort | staug copy paste based image augmentation technique using salient target |
| topic | Copy-paste image augmentation plant disease classifier salient object detection |
| url | https://ieeexplore.ieee.org/document/9961191/ |
| work_keys_str_mv | AT jisookang staugcopypastebasedimageaugmentationtechniqueusingsalienttarget AT kyungyongchung staugcopypastebasedimageaugmentationtechniqueusingsalienttarget |