scholarly journals Methods for Preventing Visual Attacks in Convolutional Neural Networks Based on Data Discard and Dimensionality Reduction

2021 ◽  
Vol 11 (11) ◽  
pp. 5235
Author(s):  
Nikita Andriyanov
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Inference ◽  
Recognition Accuracy ◽  
Network Architectures ◽  
Reduced Dimensions ◽  
Different Types ◽  
Rectangular Area ◽  
Noise Impulse ◽  
Selection Of

The article is devoted to the study of convolutional neural network inference in the task of image processing under the influence of visual attacks. Attacks of four different types were considered: simple, involving the addition of white Gaussian noise, impulse action on one pixel of an image, and attacks that change brightness values within a rectangular area. MNIST and Kaggle dogs vs. cats datasets were chosen. Recognition characteristics were obtained for the accuracy, depending on the number of images subjected to attacks and the types of attacks used in the training. The study was based on well-known convolutional neural network architectures used in pattern recognition tasks, such as VGG-16 and Inception_v3. The dependencies of the recognition accuracy on the parameters of visual attacks were obtained. Original methods were proposed to prevent visual attacks. Such methods are based on the selection of “incomprehensible” classes for the recognizer, and their subsequent correction based on neural network inference with reduced image sizes. As a result of applying these methods, gains in the accuracy metric by a factor of 1.3 were obtained after iteration by discarding incomprehensible images, and reducing the amount of uncertainty by 4–5% after iteration by applying the integration of the results of image analyses in reduced dimensions.

scholarly journals Evaluation of CNN, Alexnet and GoogleNet for Fruit Recognition

2018 ◽  
Vol 12 (2) ◽  
pp. 468 ◽  
Author(s):  
Nur Azida Muhammad ◽  
Amelina Ab Nasir ◽  
Zaidah Ibrahim ◽  
Nurbaity Sabri
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Convolutional Neural Network ◽  
Recognition Accuracy ◽  
Weather Condition ◽  
Experimental Results ◽  
Human Intervention ◽  
Recognition Result ◽  
Different Types

Fruit recognition is useful for automatic fruit harvesting. Fruit recognition application can reduce or minimize human intervention during fruit harvesting operation. However, in computer vision, fruit recognition is very challenging because of similar shapes, colors and textures among various fruits. Illuminations changes due to weather condition also leads to a challenging task for fruit recognition. Thus, this paper tends to investigate the performance of basic Convolutional Neural Network (CNN), Alexnet and Googlenet in recognizing nine different types of fruits from a publicly available dataset.  The experimental results indicate that all these techniques produce excellent recognition accuracy, but basic CNN achieves the fastest recognition result compared with Alexnet and Googlenet.

scholarly journals Comparing bags of features, conventional convolutional neural network and AlexNet for fruit recognition

2019 ◽  
Vol 14 (1) ◽  
pp. 333 ◽  
Author(s):  
Nik Noor Akmal Abdul Hamid ◽  
Rabiatul Adawiya Razali ◽  
Zaidah Ibrahim
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Recognition Accuracy ◽  
Recognition Performance ◽  
Operation Time ◽  
Machine Learning Techniques ◽  
Bag Of Features ◽  
Learning Techniques ◽  
Recognition Result ◽  
Different Types

This paper presents a comparative study between Bag of Features (BoF), Conventional Convolutional Neural Network (CNN) and Alexnet for fruit recognition.  Automatic fruit recognition can minimize human intervention in their fruit harvesting operations, operation time and harvesting cost.  On the other hand, this task is very challenging because of the similarities in shapes, colours and textures among various types of fruits. Thus, a robust technique that can produce good result is necessary. Due to the outstanding performance of deep learning like CNN and its pre-trained models like AlexNet in image recognition, this paper investigates the accuracy of conventional CNN, and Alexnet in recognizing thirty different types of fruits from a publicly available dataset.  Besides that, the recognition performance of BoF is also examined since it is one of the machine learning techniques that achieves good result in object recognition.   The experimental results indicate that all of these three techniques produce excellent recognition accuracy. Furthermore, conventional CNN achieves the fastest recognition result compared to BoF, and Alexnet.

scholarly journals Image Registration Algorithm Based on Convolutional Neural Network and Local Homography Transformation

2020 ◽  
Vol 10 (3) ◽  
pp. 732 ◽  
Author(s):  
Yuanwei Wang ◽  
Mei Yu ◽  
Gangyi Jiang ◽  
Zhiyong Pan ◽  
Jiqiang Lin
Keyword(s):  
Neural Network ◽  
Image Registration ◽  
Convolutional Neural Network ◽  
Estimation Algorithm ◽  
Matrix Estimation ◽  
Registration Algorithm ◽  
Image Registration Algorithm ◽  
Different Types ◽  
Homography Transformation ◽  
Traditional Image

In order to overcome the poor robustness of traditional image registration algorithms in illuminating and solving the problem of low accuracy of a learning-based image homography matrix estimation algorithm, an image registration algorithm based on convolutional neural network (CNN) and local homography transformation is proposed. Firstly, to ensure the diversity of samples, a sample and label generation method based on moving direct linear transformation (MDLT) is designed. The generated samples and labels can effectively reflect the local characteristics of images and are suitable for training the CNN model with which multiple pairs of local matching points between two images to be registered can be calculated. Then, the local homography matrices between the two images are estimated by using the MDLT and finally the image registration can be realized. The experimental results show that the proposed image registration algorithm achieves higher accuracy than other commonly used algorithms such as the SIFT, ORB, ECC, and APAP algorithms, as well as another two learning-based algorithms, and it has good robustness for different types of illumination imaging.

Sign in / Sign up

Export Citation Format

Share Document