A new method for image classification and image retrieval using convolutional neural networks

This article proposes a new method for image classification and image retrieval. The advantages of the proposed method are its high performance and requiring less memory compared to other methods. In order to extract image features, a Convolutional Neural Network (CNN), AlexNet, has been used. For image classification, we design a committee of four classifiers trained on graphics cards, narrowing the gap to human performance. For image retrieval, the similarity between extracted features from dataset images and features of the query image is calculated and the final results are visualized. Comprehensive experiments on Corel‐1k, Corel‐10k, Caltech‐101 object and Scene‐67 datasets have been investigated to find optimal parameters of the proposed method. The experiments demonstrate the high performance of the proposed method in comparison with the state‐of‐the‐art in the field.

[1]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[2]  Jing-Ming Guo,et al.  Content-Based Image Retrieval Using Features Extracted From Halftoning-Based Block Truncation Coding , 2015, IEEE Transactions on Image Processing.

[3]  Jiajun Wu,et al.  Deep multiple instance learning for image classification and auto-annotation , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[5]  Gholam Ali Montazer,et al.  Scene Classification Based on Local Binary Pattern and Improved Bag of Visual Words , 2015, IWANN.

[6]  Wei Yuan,et al.  Multi-view manifold learning with locality alignment , 2018, Pattern Recognit..

[7]  Maisa Daoud,et al.  Content-Based Image Retrieval Using SOM and DWT , 2015 .

[8]  Xiaodong Cui,et al.  Data augmentation for deep convolutional neural network acoustic modeling , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[9]  Davar Giveki,et al.  Scale-space multi-view bag of words for scene categorization , 2020, Multim. Tools Appl..

[10]  Gholam Ali Montazer,et al.  Atanassov's intuitionistic fuzzy histon for robust moving object detection , 2017, Int. J. Approx. Reason..

[11]  Gholam Ali Montazer,et al.  Extended Bag of Visual Words for Face Detection , 2015, IWANN.

[12]  Bolei Zhou,et al.  Learning Deep Features for Scene Recognition using Places Database , 2014, NIPS.

[13]  Gholam Ali Montazer,et al.  An improved radial basis function neural network for object image retrieval , 2015, Neurocomputing.

[14]  Xin Yuan,et al.  A Deep Generative Deconvolutional Image Model , 2016, AISTATS.

[15]  Jie Xie,et al.  Investigation of acoustic and visual features for acoustic scene classification , 2019, Expert Syst. Appl..

[16]  Gholam Ali Montazer,et al.  A new image feature descriptor for content based image retrieval using scale invariant feature transform and local derivative pattern , 2017 .

[17]  Jing-Yu Yang,et al.  Content-based image retrieval using computational visual attention model , 2015, Pattern Recognit..

[18]  Stephen Lin,et al.  FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Zahid Mehmood,et al.  A Novel Image Retrieval Based on a Combination of Local and Global Histograms of Visual Words , 2016 .

[20]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[21]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[22]  Fan Zhang,et al.  Deep Convolutional Neural Networks for Hyperspectral Image Classification , 2015, J. Sensors.

[23]  Muhammad Arif Shah,et al.  Improving CBIR accuracy using convolutional neural network for feature extraction , 2017, 2017 13th International Conference on Emerging Technologies (ICET).

[24]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[25]  Heba A. Elnemr,et al.  Combining SURF and MSER along with Color Features for Image Retrieval System Based on Bag of Visual Words , 2016, J. Comput. Sci..

[26]  Zahid Mehmood,et al.  Content-Based Image Retrieval Based on Visual Words Fusion Versus Features Fusion of Local and Global Features , 2018 .

[27]  Age K. Smilde,et al.  UvA-DARE ( Digital Academic Repository ) Assessment of PLSDA cross validation , 2008 .

[28]  Feng Zhang,et al.  Image Retrieval Based on Fused CNN Features , 2017 .

[29]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[30]  Davar Giveki,et al.  Scene classification using a new radial basis function classifier and integrated SIFT–LBP features , 2020, Pattern Analysis and Applications.

[31]  Taghi M. Khoshgoftaar,et al.  A survey of transfer learning , 2016, Journal of Big Data.

[32]  Andrew Zisserman,et al.  Image Classification using Random Forests and Ferns , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[33]  Davar Giveki.  Improving the Performance of Convolutional Neural Networks for Image Classification , 2021 .

[34]  Xiangyang Wang,et al.  Content-based image retrieval using local visual attention feature , 2014, J. Vis. Commun. Image Represent..

[35]  Gholam Ali Montazer,et al.  Scene Classification Using Multi-Resolution WAHOLB Features and Neural Network Classifier , 2017, Neural Processing Letters.

[36]  Davar Giveki,et al.  Robust moving object detection based on fusing Atanassov's Intuitionistic 3D Fuzzy Histon Roughness Index and texture features , 2021, Int. J. Approx. Reason..

[37]  M. Esmel ElAlami,et al.  A new matching strategy for content based image retrieval system , 2014, Appl. Soft Comput..

[38]  Jasman Pardede,et al.  Re-weighting Relevance Feedback in HSV Quantization for CBIR , 2018, 2018 19th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD).

[39]  Léon Bottou,et al.  Stochastic Gradient Descent Tricks , 2012, Neural Networks: Tricks of the Trade.

[40]  Davar Giveki,et al.  A New Content Based Image Retrieval Model Based on Wavelet Transform , 2015 .

[41]  Zahid Mehmood,et al.  An effective content-based image retrieval technique for image visuals representation based on the bag-of-visual-words model , 2018, PloS one.

[42]  Gholam Ali Montazer,et al.  Content based image retrieval system using clustered scale invariant feature transforms , 2015 .

[43]  Davar Giveki,et al.  Proposing a new feature descriptor for moving object detection , 2020 .