RETRACTED ARTICLE: Performance enhancement of generative adversarial network for photograph–sketch identification

• Published in: Soft computing (Berlin, Germany) Vol. 27; no. 1; pp. 435 - 452
• Main Authors: Sannidhan, M. S., Prabhu, G. Ananth, Chaitra, K. M., Mohanty, Jnyana Ranjan
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 2023; Springer Nature B.V
• Subjects: Accuracy; Artificial Intelligence; Biometrics; Classification; Computational Intelligence; Computer vision; Control; Datasets; Engineering; Focus; Generative adversarial networks; Identification; Image enhancement; Mathematical Logic and Foundations; Mechatronics; Performance enhancement; Robotics; Sketches; Gamma correction technique; Deep neural network; Sketch recognition; Sketch to photogeneration; Transfer learning; Generative adversarial network
• ISSN: 1432-7643; 1433-7479
• DOI: 10.1007/s00500-021-05700-w

Usage of sketches for offender recognition has turned out to be one of the law enforcement agencies and defense systems’ typical practices. Usual practices involve producing a convict’s sketch through the crime observer’s explanations. Nevertheless, researches have effectively proved the failure of customary practices as they carry a maximum level of discrepancies in the process of identification. The advent of computer vision techniques has replaced this traditional procedure with intelligent machines capable of ruling out the possible discrepancies, thus assisting the investigation process and considering the relevant points mentioned earlier. This research paper has investigated an adversarial network toward achieving color photograph images out of sketches, which are then classified using pre-trained transfer learning models to accomplish the identification process. Further, to enhance the adversarial network’s performance factor in terms of photogeneration, we also employed a novel sketch generator based on the gamma adjustment technique. Experimental trials are steered with image datasets open to the research community. The trials’ outcomes evidenced that the proposed system achieved the lowest similarity score of 91% and the average identification accuracy of more than 70% on all the datasets. Comparative analysis portrayed in this work also attests that the proposed technique performs ably better than any other state-of-the-art techniques.