2017/09/01 by Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib · 2 citations
Computer Science · Engineering · #Filter (signal processing) #Image (mathematics) #Image Enhancement Techniques #Image Retrieval and Classification Techniques #Image and Video Quality Assessment #Image texture #Matching (statistics) #Metric (unit) #Pattern recognition (psychology) #Set (abstract data type) #Similarity (geometry) #Unsupervised learning #cs.CV #cs.MM #eess.IV #eess.SP
paper · pdf · doi:10.1109/icip.2017.8296841
published as 2017 IEEE International Conference on Image Processing (ICIP), Beijing, 2017, pp. 3041-3045 · Paper:5 pages, 5 figures, 3 tables and Poster [Ancillary files]
openalex publication_date 2017/09/01 · openalex created_date 2017/09/25 · arxiv created 2018/11/21 · arxiv updated 2018/11/26 · openalex updated_date 2026/08/05
In this paper, we introduce an adaptive unsupervised learning framework, which utilizes natural images to train filter sets. The applicability of these filter sets is demonstrated by evaluating their performance in two contrasting applications - image quality assessment and texture retrieval. While assessing image quality, the filters need to capture perceptual differences based on dissimilarities between a reference image and its distorted version. In texture retrieval, the filters need to assess similarity between texture images to retrieve closest matching textures. Based on experiments, we show that the filter responses span a set in which a monotonicity-based metric can measure both the perceptual dissimilarity of natural images and the similarity of texture images. In addition, we corrupt the images in the test set and demonstrate that the proposed method leads to robust and reliable retrieval performance compared to existing methods.