No abstract

Face recognition is one of the most successful applications of image analysis and understanding and has gained much attention in recent years. Various algorithms were proposed and research groups across the world reported different and often contradictory results when comparing them. The aim of this paper is to present an independent, comparative study of three most popular appearance-based face recognition projection methods (PCA, ICA, and LDA) in completely equal working conditions regarding preprocessing and algorithm implementation. We are motivated by the lack of direct and detailed independent comparisons of all possible algorithm implementations (e.g., all projection-metric combinations) in available literature. For consistency with other studies, FERET data set is used with its standard tests (gallery and probe sets). Our results show that no particular projection-metric combination is the best across all standard FERET tests and the choice of appropriate projection-metric combination can only be made for a specific task. Our results are compared to other available studies and some discrepancies are pointed out. As an additional contribution, we also introduce our new idea of hypothesis testing across all ranks when comparing performance results.

Abstract-The aim of this paper is to examine a set of wavelet functions (wavelets) for implementation in a still image compression system and to highlight the benefit of this transform relating to today's methods. The paper discusses important features of wavelet transform in compression of still images, including the extent to which the quality of image is degraded by the process of wavelet compression and decompression. Image quality is measured objectively, using peak signal-to-noise ratio or picture quality scale, and subjectively, using perceived image quality. The effects of different wavelet functions, image contents and compression ratios are assessed. A comparison with a discrete-cosine-transform-based compression system is given. Our results provide a good reference for application developers to choose a good wavelet compression system for their application.

The increasing availability of large digitized fine art collections opens new research perspectives in the intersection of artificial intelligence and art history. Motivated by the successful performance of Convolutional Neural Networks (CNN) for a wide variety of computer vision tasks, in this paper we explore their applicability for art-related image classification tasks. We perform extensive CNN fine-tuning experiments and consolidate in one place the results for five different art-related classification tasks on three large fine art datasets. Along with addressing the previously explored tasks of artist, genre, style and time period classification, we introduce a novel task of classifying artworks based on their association with a specific national artistic context. We present state-of-the-art classification results of the addressed tasks, signifying the impact of our method on computational analysis of art, as well as other image classification related research areas. Furthermore, in order to question transferability of deep representations across various source and target domains, we systematically compare the effects of domain-specific weight initialization by evaluating networks pre-trained for different tasks, varying from object and scene recognition to sentiment and memorability labelling. We show that fine-tuning networks pre-trained for scene recognition and sentiment prediction yields better results than fine-tuning networks pre-trained for object recognition. This novel outcome of our work suggests that the semantic correlation between different domains could be inherent in the CNN weights. Additionally, we address the practical applicability of our results by analysing different aspects of image similarity. We show that features derived from fine-tuned networks can be employed to retrieve images similar in either style or content, which can be used to enhance capabilities of search systems in different online art collections.

In this paper we present new image quality database VCL@FER (http://www.vcl.fer.hr/quality/) which consists of four degradation types, 6 levels of each degradation and 23 different images (552 degraded images). It can be used in objective image quality evaluation, as well as to develop and test new image quality measures. Results for six commonly used full reference objective quality measures are compared using newly developed image database, as well as 6 other image databases.