Context-based image re-ranking for content-based image retrieval

Li, Jiyi

doi:10.1109/cimsivp.2011.5949252

Cited by 2 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to use these massive amounts of unlabeled data, the researchers proposed deep unsupervised hashing method. The learning process of the hash code in the early deep unsupervised hashing method was completed by the deep autoencoder [27,28]. However, the variability of natural images in terms of position, color, posture, etc., affected the representativeness of the learned hash code.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Hashing with Gradient Attention

et al. 2020

View full text Add to dashboard Cite

The existing learning-based unsupervised hashing method usually uses a pre-trained network to extract features, and then uses the extracted feature vectors to construct a similarity matrix which guides the generation of hash codes through gradient descent. Existing research shows that the algorithm based on gradient descent will cause the hash codes of the paired images to be updated toward each other’s position during the training process. For unsupervised training, this situation will cause large fluctuations in the hash code during training and limit the learning efficiency of the hash code. In this paper, we propose a method named Deep Unsupervised Hashing with Gradient Attention (UHGA) to solve this problem. UHGA mainly includes the following contents: (1) use pre-trained network models to extract image features; (2) calculate the cosine distance of the corresponding features of the pair of images, and construct a similarity matrix through the cosine distance to guide the generation of hash codes; (3) a gradient attention mechanism is added during the training of the hash code to pay attention to the gradient. Experiments on two existing public datasets show that our proposed method can obtain more discriminating hash codes.

show abstract

Section: Introductionmentioning

confidence: 99%

Unsupervised Hashing with Gradient Attention

et al. 2020

View full text Add to dashboard Cite

show abstract

“…1.1 CBIR: Content based image retrieval [1] is based on (automated) matching of the features of the query image with that of image database through some image-image similarity evaluation. Therefore, the images will be indexed according to their own visual content in the light of the underlying (chosen) features like color (distribution of color intensity across image, texture (presence of visual patterns that have properties of homogeneity and do not result from the presence of single color, or intensity), shape (boundaries, or the interiors of objects depicted in the image), or any other visual feature or combination of a set of elementary visual features.…”

Section: Introductionmentioning

confidence: 99%

Multimodel Local Terenary Patterns for Content Based Image Retrieval

Palvi¹

2017

ijarcs

View full text Add to dashboard Cite

CBIR is the field of digital media that plays important role for extraction of relevant information from media dataset based on various contents. These contents are signals, shapes, and texture and colour compositions. Texture feature provide information about the background of the images and content of the images. LBP has been widely used for texture feature extraction. LBP has major drawback of sensitivity to noise and irregularity at edges. In this paper a novel approach has been utilized for texture feature extraction from the colour images. LTP approach has been used for feature extraction from the colour images so that effective information about the image regions has been computed. Texture features have been computed by decomposing image into various small regions and these features have been concatenated to a single vector. On the basis of proposed model performance we can analyse that proposed system provide better result than existing one.

show abstract

Context-based image re-ranking for content-based image retrieval

Cited by 2 publications

References 12 publications

Unsupervised Hashing with Gradient Attention

Unsupervised Hashing with Gradient Attention

Multimodel Local Terenary Patterns for Content Based Image Retrieval

Contact Info

Product

Resources

About