{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T08:10:23Z","timestamp":1768637423266,"version":"3.49.0"},"reference-count":0,"publisher":"IGI Global","issue":"1","license":[{"start":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T00:00:00Z","timestamp":1764288000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/3.0\/deed.en_US"},{"start":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T00:00:00Z","timestamp":1764288000000},"content-version":"am","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/3.0\/deed.en_US"},{"start":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T00:00:00Z","timestamp":1764288000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/3.0\/deed.en_US"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,28]]},"abstract":"<p>Hybrid-source image separation often faces challenges, such as structural information loss, texture blurring, and training instability. To address these issues, a structurally optimized generative adversarial network (GAN) method was developed. The proposed framework integrates the Wasserstein GAN with gradient penalty [SL1.1] with multiscale residual connections and a channel attention mechanism, thereby enhancing structural representation and texture restoration of source images. A composite loss function\u2014comprising adversarial loss, reconstruction loss, perceptual loss, and structural similarity index loss\u2014was designed to balance image fidelity and perceptual feature reconstruction during training. Extensive experiments on the public hybrid-source image datasets Mixed-CelebA and MixtureCOCO demonstrated that the proposed method outperforms conventional separation models. These results suggest that the proposed approach provides an effective and practical solution for hybrid-source image separation in complex scenarios.<\/p>","DOI":"10.4018\/ijitsa.394242","type":"journal-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:51:09Z","timestamp":1764355869000},"page":"1-19","source":"Crossref","is-referenced-by-count":0,"title":["Generative Adversarial Network Optimization Methods for Hybrid-Source Image Separation"],"prefix":"10.4018","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7045-9683","authenticated-orcid":true,"given":"Qiang","family":"Geng","sequence":"first","affiliation":[{"name":"School of Big Data, Chongqing College of Mobile Communication, China & Chongqing Key Laboratory of Public Big Data Security Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1906-4125","authenticated-orcid":true,"given":"Yu","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Big Data, Chongqing College of Mobile Communication, China & Chongqing Key Laboratory of Public Big Data Security Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixuan","family":"Geng","sequence":"additional","affiliation":[{"name":"University of Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"2432","container-title":["International Journal of Information Technologies and Systems Approach"],"original-title":[],"language":"ng","link":[{"URL":"https:\/\/www.igi-global.com\/viewtitle.aspx?TitleId=394242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T20:59:56Z","timestamp":1768597196000},"score":1,"resource":{"primary":{"URL":"https:\/\/services.igi-global.com\/resolvedoi\/resolve.aspx?doi=10.4018\/IJITSA.394242"}},"subtitle":[""],"short-title":[],"issued":{"date-parts":[[2025,11,28]]},"references-count":0,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"URL":"https:\/\/doi.org\/10.4018\/ijitsa.394242","relation":{},"ISSN":["1935-570X","1935-5718"],"issn-type":[{"value":"1935-570X","type":"print"},{"value":"1935-5718","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,28]]}}}