An automatic gender recognition algorithm based on machine learning methods is proposed. It consists of two stages: adaptive feature extraction and support vector machine classification. Both training technique of the proposed algorithm and experimental results acquired on a large image dataset are presented.
Ringing artifacts arise near edges in highly compressed JPEG2000 images. This paper is devoted to the study of the optimal bilateral filter parameter selection in image deringing. We propose modification of the bilateral filter: adaptive bilateral filter, where parameters of bilateral filter are changing according to the corresponding pixel. On the first… (More)
Ringing artifacts arise near edges in highly compressed JPEG2000 images. This paper proposes original image ringing detection and suppression techniques. On the first stage edge detection and ringing estimation algorithms are applied to calculate the ringing map of a compressed input image. On the second stage this ringing map is utilized to adjust the… (More)
– In this paper a new approach to the problem of impulse noise removal from color images is presented. The proposed method is based on noise detection algorithm and weighted vector median filter. The results of its analysis compared to other known median-based vector filters are presented. The analysis shows that the proposed algorithm is more efficient in… (More)
Modified progressive switching median filter is proposed. It is constructed using introduction of the impulse noise detector from adaptive switching median filter into the progressive switching median filter. The results of comparative analysis of new algorithm with other filters are presented. The results show that the proposed algorithm is more efficient… (More)
—The real-time audience measurement system consists of five consecutive stages: face detection, face tracking, gender recognition, age classification and in-cloud data statistics analysis. The challenging part of such system is age estimation algorithm on the basis of machine learning methods. The face aging process is determined by different factors:… (More)