A Sustainable Deep Learning Framework for Object Recognition Using Multi-Layers Deep Features Fusion and Selection

Abstract

With an overwhelming increase in the demand of autonomous systems, especially in the applications related to intelligent robotics and visual surveillance, come stringent accuracy requirements for complex object recognition. A system that maintains its performance against a change in the object’s nature is said to be sustainable and it has become a major area of research for the computer vision research community in the past few years. In this work, we present a sustainable deep learning architecture, which utilizes multi-layer deep features fusion and selection, for accurate object classification. The proposed approach comprises three steps: (1) By utilizing two deep learning architectures, Very Deep Convolutional Networks for Large-Scale Image Recognition and Inception V3, it extracts features based on transfer learning, (2) Fusion of all the extracted feature vectors is performed by means of a parallel maximum covariance approach, and (3) The best features are selected using Multi Logistic Regression controlled Entropy-Variances method. For verification of the robust selected features, the Ensemble Learning method named Subspace Discriminant Analysis is utilized as a fitness function. The experimental process is conducted using four publicly available datasets, including Caltech-101, Birds database, Butterflies database and CIFAR-100, and a ten-fold validation process which yields the best accuracies of 95.5%, 100%, 98%, and 68.80% for the datasets respectively. Based on the detailed statistical analysis and comparison with the existing methods, the proposed selection method gives significantly more accuracy. Moreover, the computational time of the proposed selection method is better for real-time implementation.

Multideep Feature Fusion Algorithm for Clothing Style Recognition

“…In this approach, there are two aspects. Firstly, the soft-NMS scoring inhibition method was used and the scoring formula was shown in equation (7). Secondly, the soft-NMS weighted adjustment method is used to adjust the weight of the candidate box's optimal position coordinates according to the score.…”

“…The computer vision technology completes the recognition and classification of images. The computer is also used to analyze and understand the image content, simulate the thinking mode of human, and automatically extract the image features [5][6][7]. At present, deep learning performs well in visual recognition, speech recognition, image recognition, and other aspects.…”

Hybrid Malware Classification Method Using Segmentation-Based Fractal Texture Analysis and Deep Convolution Neural Network Features

“…In recent times, deep learning has confirmed its supremacy for many computer vision and machine learning applications like action recognition [16], gait recognition [17,18], object detection [19,20], and many more [21][22][23]. For malware detection and classification, different researchers have applied deep learning and image processing techniques to accomplish high accuracy because of their ground-breaking capacity to learn the best features.…”

Multimodal Brain Tumor Classification Using Deep Learning and Robust Feature Selection: A Machine Learning Application for Radiologists

“…Another well-known technique of deep learning is convolutional neural networks (CNN), which shows excellent performance both for 2D and 3D medical images [ 9 , 10 ]. Similarly, the transfer learning technique is typically utilized in case of limited availability of data and computational resources to save time [ 11 ]. This technique uses the knowledge acquired for one task to solve related ones [ 12 ].…”