Visual attention mechanism and support vector machine based automatic image annotation

Abstract

Automatic image annotation not only has the efficiency of text-based image retrieval but also achieves the accuracy of content-based image retrieval. Users of annotated images can locate images they want to search by providing keywords. Currently most automatic image annotation algorithms do not consider the relative importance of each region in the image, and some algorithms extract the image features as a whole. This makes it difficult for annotation words to reflect salient versus non-salient areas of the image. Users searching for images are usually only interested in the salient areas. We propose an algorithm that integrates a visual attention mechanism with image annotation. A preprocessing step divides the image into two parts, the salient regions and everything else, and the annotation step places a greater weight on the salient region. When the image is annotated, words relating to the salient region are given first. The support vector machine uses particle swarm optimization to annotate the images automatically. Experimental results show the effectiveness of the proposed algorithm.

The Frequency of Common Deafness-Associated Variants Among 3,555,336 Newborns in China and 141,456 Individuals Across Seven Populations Worldwide

“…In addition, the most frequent variant was GJB2 c.235delC, and its frequency was extraordinarily high compared with those of other variants detected in this study, with an allele frequency of 0.99%. When compared with other Asian populations, this frequency was similar to those found among the general populations in the Korea (0.500%–0.744%) (Park et al 2000, 2003; Bae et al 2008; Han et al 2008; Sagong et al 2013) and Japan (0.426%–0.786%) (Kudo et al 2000; Tsukada et al 2010; Taniguchi et al 2015; Maeda et al 2020) and previously studied Chinese populations (0.638%–1.229%) (Table 3) (Wu et al 2011; Zhang et al 2012; Chen et al 2015; Peng et al 2016; Wu et al 2017; Hao et al 2018; He et al 2018; Dai et al 2019; Zou et al 2019; Cao et al 2020, 2022; Cai et al 2021). GJB2 encodes the gap junction protein connexin 26 (Cx26), which is expressed in the nonsensory cells of the cochlea.…”

“…There is considerable genetic heterogeneity in HL among various ethnic and regional groups (Sloan-Heggen et al 2016), so it is important to recognize hotspot variants for particular ethnic populations. Although genetic analysis of newborns from China, the United States, Italy, Hungary, Spain, Croatia, and Brazil (Niceta et al 2007; Zaputovic et al 2008; Nagy et al 2010; Nivoloni et al 2010; Streitenberger et al 2011; Lim et al 2013; Hao et al 2018) has been reported, no large-scale study has compared the newborn variant frequencies of common deafness-associated genes among different geographical populations. Such a study would provide ethnic-specific variant information to improve the efficacy of newborn genetic screening.…”

Harmonic Mean based Classification of Images using Weighted Nearest Neighbor for Tagging

“…The method was proposed for image annotation refinement using a two-pass kNN classifier and group sparse reconstruction algorithm in [16]. The method for annotation of images using visual attention mechanism and SVM particle swarm optimization was presented in [17]. The method to suggest tags for an image based on visual features and tag correlations using a neighbor voting scheme was proposed in [18].…”

Image Tag Recommendation based on Ranked Categorical Nearest Neighbors and Weighted Tag Features

“…Finally, the tags are recommended based on the category of an input image. In [2] the method was proposed labeling of the images. The images were segmented into regions and identified salient region.…”