scholarly journals Composite Binary Decomposition Networks

2019 ◽  
Vol 33 ◽  
pp. 4747-4754
Author(s):  
You Qiaoben ◽  
Zheng Wang ◽  
Jianguo Li ◽  
Yinpeng Dong ◽  
Yu-Gang Jiang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Object Detection ◽  
Image Classification ◽  
Semantic Segmentation ◽  
Low Rank ◽  
Training Procedure ◽  
Binary Decomposition

Binary neural networks have great resource and computing efficiency, while suffer from long training procedure and non-negligible accuracy drops, when comparing to the fullprecision counterparts. In this paper, we propose the composite binary decomposition networks (CBDNet), which first compose real-valued tensor of each layer with a limited number of binary tensors, and then decompose some conditioned binary tensors into two low-rank binary tensors, so that the number of parameters and operations are greatly reduced comparing to the original ones. Experiments demonstrate the effectiveness of the proposed method, as CBDNet can approximate image classification network ResNet-18 using 5.25 bits, VGG-16 using 5.47 bits, DenseNet-121 using 5.72 bits, object detection networks SSD300 using 4.38 bits, and semantic segmentation networks SegNet using 5.18 bits, all with minor accuracy drops.1

scholarly journals Data Augmentation Methods Applying Grayscale Images for Convolutional Neural Networks in Machine Vision

2021 ◽  
Vol 11 (15) ◽  
pp. 6721
Author(s):  
Jinyeong Wang ◽  
Sanghwan Lee
Keyword(s):  
Neural Networks ◽  
Machine Vision ◽  
Object Detection ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Data Augmentation ◽  
Image Data ◽  
Manufacturing Productivity ◽  
Smart Factories ◽  
Grayscale Images

In increasing manufacturing productivity with automated surface inspection in smart factories, the demand for machine vision is rising. Recently, convolutional neural networks (CNNs) have demonstrated outstanding performance and solved many problems in the field of computer vision. With that, many machine vision systems adopt CNNs to surface defect inspection. In this study, we developed an effective data augmentation method for grayscale images in CNN-based machine vision with mono cameras. Our method can apply to grayscale industrial images, and we demonstrated outstanding performance in the image classification and the object detection tasks. The main contributions of this study are as follows: (1) We propose a data augmentation method that can be performed when training CNNs with industrial images taken with mono cameras. (2) We demonstrate that image classification or object detection performance is better when training with the industrial image data augmented by the proposed method. Through the proposed method, many machine-vision-related problems using mono cameras can be effectively solved by using CNNs.

Multimodal Neural Networks: RGB-D for Semantic Segmentation and Object Detection

2017 ◽  
pp. 98-109 ◽  
Author(s):  
Lukas Schneider ◽  
Manuel Jasch ◽  
Björn Fröhlich ◽  
Thomas Weber ◽  
Uwe Franke ◽  
...  
Keyword(s):  
Neural Networks ◽  
Object Detection ◽  
Semantic Segmentation

scholarly journals Assessing Wear Out of Tyre using Opencv & Convolutional Neural Networks

2021 ◽  
Vol 2089 (1) ◽  
pp. 012001
Author(s):  
C Kishor Kumar Reddy ◽  
P R Anisha ◽  
R Madana Mohana
Keyword(s):  
Neural Networks ◽  
Object Detection ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Wear Testing ◽  
Timely Manner ◽  
Safe Driving ◽  
The Road ◽  
Tire Wear ◽  
Wear And Tear

Abstract This work proposes a process to detect the wear and tear of car tires. Tire is the only part of the road that does not interact with the road. The condition of the wheel should therefore be monitored in a timely manner for safe driving. Tired fatigue occurs due to limitations such as that the tread limit is less than 1.6 cm, the damage to the rubber, where there are pipes around 4 to 5, the affected tire. We look at some of the above limitations of tire wear testing using computer viewing techniques such as opencv and convolutional neural networks. Opencv and convolutional neural networks are widely used for object detection and image classification. We used these methods and obtained 90.90% accuracy, with which we can predict tire wear to avoid dangerous accidents..

scholarly journals Towards Interpretable Semantic Segmentation via Gradient-Weighted Class Activation Mapping (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13943-13944
Author(s):  
Kira Vinogradova ◽  
Alexandr Dibrov ◽  
Gene Myers
Keyword(s):  
Neural Networks ◽  
Image Segmentation ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Image Recognition ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Wide Range ◽  
Gradient Based ◽  
Activation Mapping

Convolutional neural networks have become state-of-the-art in a wide range of image recognition tasks. The interpretation of their predictions, however, is an active area of research. Whereas various interpretation methods have been suggested for image classification, the interpretation of image segmentation still remains largely unexplored. To that end, we propose seg-grad-cam, a gradient-based method for interpreting semantic segmentation. Our method is an extension of the widely-used Grad-CAM method, applied locally to produce heatmaps showing the relevance of individual pixels for semantic segmentation.

scholarly journals Real Time Object Detection using CNN

2018 ◽  
Vol 7 (2.24) ◽  
pp. 33
Author(s):  
Akash Tripathi ◽  
T V. Ajay Kumar ◽  
Tarun Kanth Dhansetty ◽  
J Selva Kumar
Keyword(s):  
Neural Networks ◽  
Object Detection ◽  
Image Classification ◽  
Real Time ◽  
Convolutional Neural Networks ◽  
Small Sample ◽  
Small Data ◽  
Processing Unit ◽  
Sift Algorithm ◽  
Central Processing

Achieving new heights in object detection and image classification was made possible because of Convolution Neural Network(CNN). However, compared to image classification the object detection tasks are more difficult to analyze, more energy consuming and computation intensive. To overcome these challenges, a novel approach is developed for real time object detection applications to improve the accuracy and energy efficiency of the detection process. This is achieved by integrating the Convolutional Neural Networks (CNN) with the Scale Invariant Feature Transform (SIFT) algorithm. Here, we obtain high accuracy output with small sample data to train the model by integrating the CNN and SIFT features. The proposed detection model is a cluster of multiple deep convolutional neural networks and hybrid CNN-SIFT algorithm. The reason to use the SIFT featureis to amplify the model‟s capacity to detect small data or features as the SIFT requires small datasets to detect objects. Our simulation results show better performance in accuracy when compared with the conventional CNN method. As the resources like RAM, graphic card, ROM, etc. are limited we propose a pipelined implementation on an aggregate Central Processing Unit(CPU) and Graphical Processing Unit(GPU) platform.  

scholarly journals Review of Image Classification Algorithms Based on Convolutional Neural Networks

2021 ◽  
Vol 13 (22) ◽  
pp. 4712
Author(s):  
Leiyu Chen ◽  
Shaobo Li ◽  
Qiang Bai ◽  
Jing Yang ◽  
Sanlong Jiang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Visual Recognition ◽  
Network Models ◽  
Semantic Segmentation ◽  
Basic Structure ◽  
Research Direction ◽  
Object Localization

Image classification has always been a hot research direction in the world, and the emergence of deep learning has promoted the development of this field. Convolutional neural networks (CNNs) have gradually become the mainstream algorithm for image classification since 2012, and the CNN architecture applied to other visual recognition tasks (such as object detection, object localization, and semantic segmentation) is generally derived from the network architecture in image classification. In the wake of these successes, CNN-based methods have emerged in remote sensing image scene classification and achieved advanced classification accuracy. In this review, which focuses on the application of CNNs to image classification tasks, we cover their development, from their predecessors up to recent state-of-the-art (SOAT) network architectures. Along the way, we analyze (1) the basic structure of artificial neural networks (ANNs) and the basic network layers of CNNs, (2) the classic predecessor network models, (3) the recent SOAT network algorithms, (4) comprehensive comparison of various image classification methods mentioned in this article. Finally, we have also summarized the main analysis and discussion in this article, as well as introduce some of the current trends.

Sign in / Sign up

Export Citation Format

Share Document