The International Arab Journal of Information Technology (IAJIT)

..............................
..............................
..............................


Deep Learning Inpainting Model on Digital and Medical Images-A Review

Image inpainting is a method to restore the missing pixels on damaged images. Initially, the traditional inpainting method uses the statistics of the surrounding pixels to find the missing pixels. It sometimes fails to read the hidden information to attain plausible imagery. The deep learning inpainting methods are introduced to overcome these challenges. A deep neural network learns the semantic priors and hidden representation pixels in an end-to-end fashion in the digital and medical. This paper discusses the following: 1) The difference between the supervised and the unsupervised deep learning inpainting algorithm used in medical and digital images. 2) Discusses the merits and demerits of each deep learning inpainting model. 3) Discusses the challenges and solution for the deep learning inpainting model. 4) Discusses each model's quantitative and qualitative analysis in the digital and other medical images.

[1] Aishwarya G. and Krishnan K., “Generative Adversarial Networks for Facial Image Inpainting and Super-Resolution,” Journal of Physics: Conference Series, vol. 2070, no. 1, pp. 1-10, 2021. doi:10.1088/1742-6596/2070/1/012103

[2] Armanious K., Kumar V., Abdulatif S., Hepp T., Gatidis S., and Yang B., “ipA-MedGAN: Inpainting of Arbitrary Regions in Medical Imaging,” in Proceedings of the IEEE International Conference on Image Processing, Abu Dhabi, pp. 3005-3009, 2020. doi: 10.1109/ICIP40778.2020.9191207

[3] Armanious K., Mecky Y., Gatidis S., and Yang B., “Adversarial Inpainting of Medical Image Modalities,” in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Brighton, pp. 3267-3271, 2019. doi: 10.1109/ICASSP.2019.8682677.

[ 4 ] Ayu s h T. a n d S a ya k P. , “Introduction to Image Inpainting with Deep Learning,” WandB, https://wandb.ai/site/articles/introduction-to- image-inpainting-with-deep-learning, Last Visited, 2023.

[5] Borole R. and Bonde S., “Patch-Based Inpainting for Object Removal and Region Filling in Images,” Journal of Intelligent Systems, vol. 22, no. 3, pp. 335-350, 2013. https://doi.org/10.1515/jisys-2013-0031

[6] Buyssens P., Daisy M., Tschumperle D., and Lezoray O., “Exemplar-based Inpainting: Technical Review and New Heuristics for Better Geometric Reconstructions,” IEEE Transactions on Image Processing, vol. 24, no. 6, pp. 1809- 1824, 2015. DOI:10.1109/TIP.2015.2411437

[7] Cai N., Su Z., Lin Z., Wang H., Yang Z., and Ling B., “Blind Inpainting Using the Fully Convolutional Neural Network,” The Visual Computer, vol. 33, no. 2, pp. 249-261, 2017. DOI: https://doi.org/10.1007/s00371-015-1190-z

[8] Chang Y., Liu Z., Lee K., and Hsu W., “Free- Form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, pp. 9066- 9075, 2019. https://doi.org/10.48550/arXiv.1904.10247

[9] Chen M., Zhao X., and Xu D., “Image Inpainting for Digital Dunhuang Mural Using Partial Convolutions and Sliding Windiw Method,” Journal of Physics: Conference Series, vol. 1302, no. 3, pp. 1-6, 2019. DOI:10.1088/1742- 6596/1302/3/032040

[10] Chen G., Zhang G., Yang Z., and Liu W., “Multi- Scale Patch-GAN with Edge Detection for Image Inpainting,” Applied Intelligence, vol. 53, no. 4, pp. 3917-3932, 2023. https://doi.org/10.1007/s10489-022-03577-2

[11] Criminisi A., Perez P., and Toyama K., “Region Filling and Object Removal by Exemplar-Based Image Inpainting,” IEEE Transactions on Image Processing, vol. 13, no. 9, pp. 1200-1212, 2004. DOI:10.1109/TIP.2004.833105

[12] Dai P., Ji S., and Zhang Y., “Gated Convolutional Networks for Cloud Removal From Bi-Temporal Remote Sensing Images,” Remote Sensing, vol. 12, no. 20, pp. 3427, 2020. https://doi.org/10.3390/rs12203427

[13] Elharrouss O., Almaadeed N., Al-Maadeed S., and Akbari Y., “Image Inpainting: A Review,” Neural Processing Letters, vol. 51, pp. 2007-2028, 2020. https://doi.org/10.1007/s11063-019-10163-0

[14] Gao X., Nguyen M., and Yan W., “Face Image Inpainting Based on Generative Adversarial Network,” in Proceedings of the 36th International Conference on Image and Vision Computing, Tauranga, pp. 1-6, 2021. DOI:10.1109/IVCNZ54163.2021.9653347

[15] Ghanem R. and Loey M., “Face Completion Using Generative Adversarial Network with Pretrained Face Landmark Generator,” International Journal of Intelligent Engineering and System, vol. 14, no. 2, pp. 295-305, 2021. DOI:10.22266/ijies2021.0430.26

[16] Hedjazi M. and Genc Y., “Efficient Texture- 934 The International Arab Journal of Information Technology, Vol. 20, No. 6, November 2023 Aware Multi-GAN for Image Inpainting,” Knowledge-Based Systems, vol. 217, no. 3, pp. 1- 24, 2021. https://doi.org/10.1016/j.knosys.2021.106789

[17] Hong X., Xiong P., Ji R., and Fan H., “Deep Fusion Network for Image Completion,” in Proceedings of the 27th ACM International Conference on Multimedia, Nice, pp. 2033-2042, 2019. https://doi.org/10.1145/3343031.3351002

[18] Kang J., Lee S., Heo S., and Lee S., “Image Inpainting Using Weighted Mask Convolution,” in Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, Auckland, pp. 1262- 1267, 2020. https://ieeexplore.ieee.org/document/9306435

[19] Kaur A., Raj A., Jayanthi N., and Indu S., “Inpainting of Irregular Holes in a Manuscript using UNet and Partial Convolution,” in Proceedings of the 2nd International Conference on Inventive Research in Computing Applications, Coimbatore, pp. 778-784, 2020. DOI:10.1109/ICIRCA48905.2020.9182917

[20] Li Z., Cai A., Wang L., Zhang W., Tang C., Li L., Liang N., Yan B., “Promising Generative Adversarial Network Based Sinogram Inpainting Method for Ultra-Limited-Angle Computed Tomography Imaging,” Sensors, vol. 19, no. 18, pp. 3941,2019. DOI:10.3390/s19183941

[21] Li Z., Zhu H., Cao L., Jiao L., Zhong Y., and Ma A., “Face Inpainting Via Nested Generative Adversarial Networks,” IEEE Access, vol. 7, pp. 155462-155471, 2019. DOI:10.1109/ACCESS.2019.2949614

[22] Liu G., Reda F., Shih K., Wang T., Tao A., and Catanzaro B., “Image Inpainting for Irregular Holes Using Partial Convolutions,” in Proceedings of the 15th European Conference on Computer Vision, Munich, pp. 89-105, 2018. https://doi.org/10.1007/978-3-030-01252-6_6

[23] Liu H., Wan Z., Huang W., Song Y., Han X., and Liao J., “PD-GAN: Probabilistic Diverse GAN for Image Inpainting,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, pp. 9371-9381, 2021. DOI:10.1109/CVPR46437.2021.00925

[24] Liu Y., Pan J., and Su Z., “Deep Blind Image Inpainting,” in Proceedings of the 19th International Conference Intelligence Science and Big Data Engineering. Visual Data Engineering, Lecture Notes in Computer Science, Nanjing, pp. 128-141, 2019. https://doi.org/10.1007/978-3- 030-36189-1_11

[25] Manjón J., Romero J., Vivo-Hernand R., Rubio G., Aparici F., De La Iglesia-Vaya M., Tourdias T., and Coupé P., “Blind MRI Brain Lesion Inpainting Using Deep Learning,” in Proceedings of the 5th International Workshop on Simulation and Synthesis in Medical Imaging, Lima, pp. 41-49, 2020. https://doi.org/10.1007/978-3-030-59520- 3_5

[26] Mo J. and Zhou Y., “The Image Inpainting Algorithm Used on Multi-Scale Generative Adversarial Networks and Neighbourhood,” Automatika: Journal for Control, Measurement, Electronics, Computing and Communications, vol. 61, no. 4, pp. 704-713, 2020. https://doi.org/10.1080/00051144.2020.1821535

[27] Mohite T. and Phadke G., “Image Inpainting with Contextual Attention and Partial Convolution,” in Proceeding of the International Conference on Artificial Intelligence and Signal Processing, Amaravati, pp. 1-6, 2020. DOI:10.1109/AISP48273.2020.9073008

[28] Patel H., Kulkarni A., Sahni S., and Vyas U., “Image Inpainting using Partial Convolution,” arXiv Preprint, arXiv:2108.08791v1, 2021.

[29] Pimkin A., Samoylenko A., Antipina N., Ovechkina A., Golanov A., Dalechina A., and Belyaev M., “Multidomain CT Metal Artifacts Reduction Using Partial Convolution Based Inpainting,” in Proceedings of the International Joint Conference on Neural Networks, Glasgow, pp. 1-6, 2020. DOI:10.1109/IJCNN48605.2020.9206625

[30] Prabhu R., Yu X., Wang Z., Liu D., and Jiang A., Inpainting and Denoising Challenges, Springer, 2019. https://doi.org/10.1007/978-3-030-25614- 2_3

[31] Salem N., Mahdi H., and Abbas H., “Random- Shaped Image Inpainting Using Dilated Convolution,” International Journal of Engineering and Advanced Technology, vol. 8, no. 6, pp. 641-647, 2019. DOI:10.35940/ijeat.F8089.088619

[32] Sami M., Naiyer I., Khan E., and Uddin J., “Improved Semantic Inpainting Architecture Augmented with a Facial Landmark Detector,” The International Arab Journal of Information Technology, vol. 19, no. 3, pp. 353-362, 2022. https://doi.org/10.34028/iajit/19/3/9

[33] Schmalfuss J., Scheurer E., Zhao H., Karantzas N., Bruhn A., and Labate D., “Blind Image Inpainting with Sparse Directional Filter Dictionaries for Lightweight CNNs,” Journal of Mathematical Imaging and Vision, vol. 65, no. 2, pp. 323-339, 2023. https://doi.org/10.1007/s10851-022-01119-6

[34] Sogancioglu E., Hu S., Belli D., and Van Ginneken, B., “Chest X-ray Inpainting with Deep Generative Models,” arXiv Preprint, arXiv:1809.01471v1, 2018.

[35] Sujaykhandekar., “Removing Objects from Pictures with Deep Learning,” Medium, https://medium.com/analytics-vidhya/removing- objects-from-pictures-with-deep-learning, Last Deep Learning Inpainting Model on Digital and Medical Images-A Review 935 Visited, 2023.

[36] Susan M., Subashini P., and Krishnaveni M., “Comparison of Various Deep Learning Inpainting Methods in Smart Colposcopy Images,” International Journal of Computational Intelligence Studies, vol. 11, no. 1, pp. 53-72, 2022. https://doi.org/10.1504/ijcistudies.2022.123347

[37] Wang X., Li P., DU Y., Lv Y., and Chen Y., “Detection and Inpainting of Specular Reflection in Colposcopic Images with Exemplar-based Method,” in Proceedings of the IEEE 13th International Conference on Anti-counterfeiting, Security, and Identification (ASID), Xiamen, pp. 90-94, 2019. DOI:10.1109/ICASID.2019.8925202

[38] Wang Y., Chen Y., Tao X., and Jia J., “VCNet: A Robust Approach to Blind Image Inpainting,” in Proceedings of the 16th European Conference on Computer Vision ECC, Glasgow, pp. 752-768, 2020. https://doi.org/10.1007/978-3-030-58595- 2_45

[39] Wei R. and Wu Y., “Image Inpainting via Context Discriminator and U-Net,” Mathematical Problems in Engineering, vol. 2022, no. 1, pp.1- 12, 2022. DOI:10.1155/2022/7328045

[40] Wu Y., Singh V., and Kapoor A., “From Image to Video Face Inpainting: Spatial-Temporal Nested GAN (STN-GAN) for Usability Recovery,” in Proceedings of the IEEE Winter Conference on Applications of Computer Vision, Snowmass, pp. 2385-2394, 2020. DOI:10.1109/WACV45572.2020.9093473

[41] Xu H., Li Q., and Chen J., “Highlight Removal from A Single Grayscale Image Using Attentive GAN,” Applied Artificial Intelligence, vol. 36, no. 1, pp. 1-19, 2022. DOI:10.1080/08839514.2021.1988441

[42] Yan S. and Zhang X., “PCNet: Partial Convolution Attention Mechanism for Image Inpainting,” International Journal of Computers and Applications, vol. 44, no. 8, pp. 738-745, 2022. https://doi.org/10.1080/08839514.2021.1988441

[43] Yan Z., Li X., Li M., Zuo W., and Shan S., “Shift- Net: Image Inpainting via Deep Feature Rearrangement,” in Proceedings of the 15th European Conference on Computer Vision ECCV, Munich, pp. 3-19, 2018. https://doi.org/10.1007/978-3-030-01264-91

[44] Yeh R., Chen C., Lim T., Schwing A., Hasegawa- Johnson M., and Do M., “Semantic Image Inpainting with Deep Generative Models,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, pp. 6882-6890, 2017. DOI:10.1109/CVPR.2017.728

[45] Yu J., Lin Z., Yang J., Shen X., Lu X., and Huang T., “Free-Form Image Inpainting with Gated Convolution,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, pp. 4470-4479, 2019. DOI:10.1109/ICCV.2019.00457

[46] Yuan L., Huang Y., and Maier A., “Projection Inpainting Using Partial Convolution for Metal Artifact Reduction,” arXiv Preprint, arXiv,abs/2005.00762, 2020. https://api.semanticscholar.org/CorpusID:218486 892

[47] Zeng Y., Fu J., Chao H., and Guo B., “Learning Pyramid-Context Encoder Network for High- Quality Image Inpainting,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, pp. 1486-1464. DOI Bookmark:10.1109/CVPR.2019.00158

[48] Zeng Y., Fu J., Chao H., and Guo B., “Aggregated Contextual Transformations for High-Resolution Image Inpainting,” IEEE Transaction on Visualization and Computer Graphics, vol. 29, no. 7, pp. 3266-3280, 2023. DOI:10.1109/TVCG.2022.3156949

[49] Zhang C. and Wang T., “Image Inpainting Using Double Discriminator Generative Adversarial Networks,” in Proceedings of the 2nd International Seminar on Computer Science and Engineering Technology, Shanghai, pp. 1-6, 2020. DOI:10.1088/1742-6596/1732/1/012052

[50] Zhang X., Wang X., Kong B., Shi C., Yin Y., Song Q., and Lyu S., “High Quality Image-based Face Inpainting using Domain Embedded Multi-model Generative Adversarial Networks,” Journal of Latex Class Files, vol. 14, no. 8, pp. 1-11, 2015. https://arxiv.org/pdf/2002.02909.pdf

[51] Zheng H., Lin Z., Lu J., Cohen S., Shechtman E., Barnes C., Zhang J., Xu N., Amirghodsi S., and Luo J., “CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Training,” arXiv Preprint, arXiv:2203.11947, 2022. https://doi.org/10.48550/arXiv.2203.11947

[52] Zhou T., Johnson B., and Li R., “Patch-based Texture Synthesis for Image Inpainting,” arXiv Preprint, arXiv, abs/1605.01576, 2016. https://arxiv.org/pdf/1605.01576.pdf

[53] Zhou X., Dai T., Jiang Y., and Xia S., “Bishift-Net for Image Inpainting,” in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Toronto, pp. 2470-2474, 2021. DOI:10.1109/ICASSP39728.2021.9413380