19 research outputs found
On Identification From Periocular Region Utilizing SIFT and SURF
No full textPublication in the conference proceedings of EUSIPCO, Lisbon, Portugal, 201
Deep learning based estimation of the eye pupil center by using image patch classification
No full textRecovery of Valuable Compounds From Apricot Concentrate Production Waste Using Supercritical Carbon Dioxide Extraction as a Green Separation Method
No full textApricot concentrate production wastewater (APW), which contains significant amounts of phenolic compounds and exhibits antioxidant activity, is also a major environmental pollutant. This study aimed to recover valuable compounds from APW and mitigate its environmental impact using the supercritical carbon dioxide (SC–CO2) extraction method. Pressure and temperature variables were studied within the ranges of 8.5–31.5 MPa and 38.5–61.5 °C, respectively. A five–level central composite design (CCD) was applied to statistically analyze the interaction between experimental conditions and results. As a result of the extraction, up to 25% yield and 3.3% total phenolic content (TPC) recovery were achieved, along with a functional extract containing over 2000 mg GAE/L phenolic substances, antioxidant activity exceeding 3000 µM TE, and a significant amount of polyunsaturated fatty acids. Using response surface methodology, the optimum conditions for SC–CO2 extraction were determined to be 60 °C and 10 MPa. Toxicity values across three trophic levels, along with selected pollution parameters, were assessed before and after the extraction. Notably, following the extraction process, the toxic classification of the wastewater, as determined by the Daphnia magna toxicity test, improved from the very toxic category (Class IV) to the toxic category (Class III). © The Author(s) 2025.Mehmet Emin Argun; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu, TÜBİTAK, (120Y351); Türkiye Bilimsel ve Teknolojik Araştırma Kurumu, TÜBİTAK; KTUN-BAP, (222301003
ON IDENTIFICATION FROM PERIOCULAR REGION UTILIZING SIFT AND SURF
No full textWe concentrate on utilization of facial periocular region for biometric identification. Although this region has superior discriminative characteristics, as compared to mouth and nose, it has not been frequently used as an independent modality for personal identification. We employ a feature-based representation, where the associated periocular image is divided into left and right sides, and descriptor vectors are extracted from these using popular feature extraction algorithms SIFT, SURF, BRISK, ORB, and LBP. We also concatenate descriptor vectors. Utilizing FLANN and Brute Force matchers, we report recognition rates and ROC. For the periocular region image data, obtained from widely used FERET database consisting of 865 subjects, we obtain Rank-1 recognition rate of 96.8% for full frontal and different facial expressions in same session cases. We include a summary of existing methods, and show that the proposed method produces lower/comparable error rates with respect to the current state of the art
How Image Degradations Affect Deep CNN-based Face Recognition?
No full textFace recognition approaches that are based on deep convolutional neural networks (CNN) have been dominating the field. The performance improvements they have provided in the so called in-the-wild datasets are significant, however, their performance under image quality degradations have not been assessed, yet. This is particularly important, since in real-world face recognition applications, images may contain various kinds of degradations due to motion blur, noise, compression artifacts, color distortions, and occlusion. In this work, we have addressed this problem and analyzed the influence of these image degradations on the performance of deep CNN-based face recognition approaches using the standard LFW closed-set identification protocol. We have evaluated three popular deep CNN models, namely, the AlexNet, VGG-Face, and GoogLeNet. Results have indicated that blur, noise, and occlusion cause a significant decrease in performance, while deep CNN models are found to be robust to distortions, such as color distortions and change in color balance
