Optimization of deep convolutional neural network for large scale image retrieval

Bai, Cong; Huang, Ling; Pan, Xiang; Zheng, Jianwei; Chen, Shengyong

doi:10.1016/j.neucom.2018.04.034

Cited by 100 publications

(39 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In particular, deep learning has made great progress in recent years [28], such as the deep neural network [29], the Boltzmann deep machine [30], the short deep network [31], etc. Among these, the deep convolutional neural network (DCNN) has already achieved many significant results in artificial vision, such as image classification [32], image segmentation [33] and object recognition [34]. The use of deep learning technology to reduce the semantic gap in the CBIR has begun in recent years [35][36].…”

Section: Related Workmentioning

confidence: 99%

An Advanced Relevance Feedback Method to Improve Performance of CBIR using Convolutional Neural Network and Comprehensive Values

Kumar¹,

Saradhi²

2019

IJEAT

View full text Add to dashboard Cite

Content-Based Image Retrieval (CBIR) is extensively used technique for image retrieval from large image databases. However, users are not satisfied with the conventional image retrieval techniques. In addition, the advent of web development and transmission networks, the number of images available to users continues to increase. Therefore, a permanent and considerable digital image production in many areas takes place. Quick access to the similar images of a given query image from this extensive collection of images pose great challenges and require proficient techniques. From query by image to retrieval of relevant images, CBIR has key phases such as feature extraction, similarity measurement, and retrieval of relevant images. However, extracting the features of the images is one of the important steps. Recently Convolutional Neural Network (CNN) shows good results in the field of computer vision due to the ability of feature extraction from the images. Alex Net is a classical Deep CNN for image feature extraction. We have modified the Alex Net Architecture with a few changes and proposed a novel framework to improve its ability for feature extraction and for similarity measurement. The proposal approach optimizes Alex Net in the aspect of pooling layer. In particular, average pooling is replaced by max-avg pooling and the non-linear activation function Maxout is used after every Convolution layer for better feature extraction. This paper introduces CNN for features extraction from images in CBIR system and also presents Euclidean distance along with the Comprehensive Values for better results. The proposed framework goes beyond image retrieval, including the large-scale database. The performance of the proposed work is evaluated using precision. The proposed work show better results than existing works.

show abstract

Section: Related Workmentioning

confidence: 99%

An Advanced Relevance Feedback Method to Improve Performance of CBIR using Convolutional Neural Network and Comprehensive Values

Kumar¹,

Saradhi²

2019

IJEAT

View full text Add to dashboard Cite

show abstract

“…Pooling not only reduces the eigenvector dimension and the number of parameters of a model but also reduces the sensitivity of the output features to factors, such as translation, rotation, and scaling, to prevent overfitting. The combination of the pooling and convolutional layers constitutes a two-time feature extraction structure, which strengthens the tolerance of a network model for distortion and enhances the robustness of the model [ 21 ].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Hyperspectral Remote Sensing Image Classification Based on Maximum Overlap Pooling Convolutional Neural Network

Yang

et al. 2018

Sensors

View full text Add to dashboard Cite

In a traditional convolutional neural network structure, pooling layers generally use an average pooling method: a non-overlapping pooling. However, this condition results in similarities in the extracted image features, especially for the hyperspectral images of a continuous spectrum, which makes it more difficult to extract image features with differences, and image detail features are easily lost. This result seriously affects the accuracy of image classification. Thus, a new overlapping pooling method is proposed, where maximum pooling is used in an improved convolutional neural network to avoid the fuzziness of average pooling. The step size used is smaller than the size of the pooling kernel to achieve overlapping and coverage between the outputs of the pooling layer. The dataset selected for this experiment was the Indian Pines dataset, collected by the airborne visible/infrared imaging spectrometer (AVIRIS) sensor. Experimental results show that using the improved convolutional neural network for remote sensing image classification can effectively improve the details of the image and obtain a high classification accuracy.

show abstract

“…A large number of these image collections pose increasing technical challenges for computer systems in order to manage image data effectively and to make such collections readily available. Many programs and tools have been developed to formulate and execute queries based on visual content and to facilitate searching through large image repositories …”

Section: Introductionmentioning

confidence: 99%

“…Many programs and tools have been developed to formulate and execute queries based on visual content and to facilitate searching through large image repositories. [1][2][3][4][5][6] Methods of image retrieval can be categorized into two approaches, 7 which are the description-based and content-based. In the description-based image retrieval approach, the retrieval is based on utilizing various methods of adding metadata to the images, such as captions, keywords, or descriptions, so that the retrieval can be performed based on these types of annotated information, whereas the content-based image retrieval (CBIR) approach differs from the description-based approach, in which the search method used in the CBIR approach analyzes the contents of the image rather than the metadata.…”

Section: Introductionmentioning

confidence: 99%

Artificial bee colony algorithm for content‐based image retrieval

Banharnsakun

2020

Computational Intelligence

View full text Add to dashboard Cite

Image retrieval is the process of searching for digital images from a large database. There exist two distinctive research groups, which employ the content‐based and description‐based approaches, respectively. However, research in the content‐based domain is currently dominant in the field, while the other approaches are not as widely utilized. Although there are a number of different techniques that are available for image retrieval, the development of more effective methods is still necessary. In recent years, previous research has shown that biologically inspired metaheuristic algorithms have great potential for use in solving problems in many science and engineering domains. The artificial bee colony (ABC) algorithm is one of the more promising biologically inspired metaheuristic approaches used to find optimal solutions as it has the advantages of convenient implementation and efficient performance. In this article, a new efficient method based on a combination of the gray‐level cooccurrence matrix (GLCM) with the ABC, referred to as “GLCM‐ABC,” is proposed for use in content‐based image retrieval (CBIR). The experimental results demonstrate that the proposed approach works well for CBIR and can classify specific types of material surfaces in images with a reasonably high level of accuracy as well as outperform other existing algorithms.

show abstract

Optimization of deep convolutional neural network for large scale image retrieval

Cited by 100 publications

References 24 publications

An Advanced Relevance Feedback Method to Improve Performance of CBIR using Convolutional Neural Network and Comprehensive Values

An Advanced Relevance Feedback Method to Improve Performance of CBIR using Convolutional Neural Network and Comprehensive Values

Hyperspectral Remote Sensing Image Classification Based on Maximum Overlap Pooling Convolutional Neural Network

Artificial bee colony algorithm for content‐based image retrieval

Contact Info

Product

Resources

About