An Evaluation of Deep Learning-Based Computer Generated Image Detection Approaches

As defect detection using machine vision is diversifying and expanding, approaches using deep learning are increasing. Recently, there have been much research for detecting and classifying defects using image segmentation, image detection, and image classification. These methods are effective but require a large number of actual defect data. However, it is very difficult to get a large amount of actual defect data in industrial areas. To overcome this problem, we propose a method for defect detection using stacked convolutional autoencoders. The autoencoders we proposed are trained by using only non-defect data and synthetic defect data generated by using the characteristics of defect based on the knowledge of the experts. A key advantage of our approach is that actual defect data is not required, and we verified that the performance is comparable to the systems trained using real defect data.

Download Full-text

Left and Right Consistent Stereo Image Detection and Classification Based on Deep Learning

Journal of Physics Conference Series ◽

10.1088/1742-6596/1575/1/012149 ◽

2020 ◽

Vol 1575 ◽

pp. 012149

Author(s):

Lijuan Tang ◽

Qing Wang ◽

Guannan Chen

Keyword(s):

Deep Learning ◽

Stereo Image ◽

Image Detection ◽

Left And Right

Download Full-text

Gradient clustering algorithm based on deep learning aerial image detection

Pattern Recognition Letters ◽

10.1016/j.patrec.2020.09.032 ◽

2021 ◽

Vol 141 ◽

pp. 37-44

Author(s):

Ning Liu ◽

Bin Guo ◽

Xinju Li ◽

Xiangyu Min

Keyword(s):

Deep Learning ◽

Clustering Algorithm ◽

Aerial Image ◽

Image Detection

Download Full-text

Medical Image Detection Using Deep Learning

Intelligent Systems Reference Library - Deep Learning in Healthcare ◽

10.1007/978-3-030-32606-7_1 ◽

2019 ◽

pp. 3-16

Author(s):

María Inmaculada García Ocaña ◽

Karen López-Linares Román ◽

Nerea Lete Urzelai ◽

Miguel Ángel González Ballester ◽

Iván Macía Oliver

Keyword(s):

Deep Learning ◽

Medical Image ◽

Image Detection

Download Full-text

Approximate Repetitive Image Detection Based on Deep Learning

2018 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS) ◽

10.1109/icitbs.2018.00166 ◽

2018 ◽

Author(s):

Bing Zhou ◽

Juan Deng ◽

Cong Li

Keyword(s):

Deep Learning ◽

Image Detection

Download Full-text

Comparative Analysis of Deep Learning Image Detection Algorithms

10.21203/rs.3.rs-132774/v1 ◽

2020 ◽

Author(s):

Shrey Srivast ◽

Amit Vishvas Divekar ◽

Chandu Anilkumar ◽

Ishika Naik ◽

Ved Kulkarni ◽

...

Keyword(s):

Image Processing ◽

Deep Learning ◽

Comparative Analysis ◽

Visual Media ◽

Image Detection ◽

Detection Algorithms ◽

Image Processing Algorithms ◽

Processing Algorithms ◽

The Moment

Abstract As humans, we do not have to strain ourselves when we interpret our surroundings through our visual senses. From the moment we begin to observe, we unconsciously train ourselves with the same set of images. Hence, distinguishing entities is not a difficult task for us. On the contrary, computer views all kinds of visual media as an array of numerical values. Due to this contrast in approach, they require image processing algorithms to examine the contents of images. This project presents a comparative analysis of 3 major image processing algorithms: SSD, Faster R-CNN, and YOLO. In this analysis, we have chosen the COCO dataset. With the help of the COCO dataset, we have evaluated the performance and accuracy of the three algorithms and analysed their strengths and weaknesses. Using the results obtained from our implementations, we determine the differences between how each algorithm runs and suitable applications for each. The parameters for evaluation are accuracy, precision, F1 score.

Download Full-text

Digital Image Art Style Transfer Algorithm Based on CycleGAN

Computational Intelligence and Neuroscience ◽

10.1155/2022/6075398 ◽

2022 ◽

Vol 2022 ◽

pp. 1-10

Author(s):

Xuhui Fu

Keyword(s):

Deep Learning ◽

Learning Technology ◽

Image Size ◽

Image Detection ◽

Style Transfer ◽

Artistic Style ◽

Multi Scale ◽

The Core ◽

Artificial Intelligence Technology ◽

Art Style

With the continuous development and popularization of artificial intelligence technology in recent years, the field of deep learning has also developed relatively rapidly. The application of deep learning technology has attracted attention in image detection, image recognition, image recoloring, and image artistic style transfer. Some image art style transfer techniques with deep learning as the core are also widely used. This article intends to create an image art style transfer algorithm to quickly realize the image art style transfer based on the generation of confrontation network. The principle of generating a confrontation network is mainly to change the traditional deconvolution operation, by adjusting the image size and then convolving, using the content encoder and style encoder to encode the content and style of the selected image, and by extracting the content and style features. In order to enhance the effect of image artistic style transfer, the image is recognized by using a multi-scale discriminator. The experimental results show that this algorithm is effective and has great application and promotion value.

Download Full-text

AD or Non-AD: A Deep Learning Approach to Detect Advertisements from Magazines

Entropy ◽

10.3390/e20120982 ◽

2018 ◽

Vol 20 (12) ◽

pp. 982 ◽

Cited By ~ 3

Author(s):

Khaled Almgren ◽

Murali Krishnan ◽

Fatima Aljanobi ◽

Jeongkyu Lee

Keyword(s):

Deep Learning ◽

Real World ◽

Marketing Strategies ◽

Multimedia Data ◽

Visual Features ◽

Image Detection ◽

Real World Application ◽

Real World Applications ◽

Scanned Images

The processing and analyzing of multimedia data has become a popular research topic due to the evolution of deep learning. Deep learning has played an important role in addressing many challenging problems, such as computer vision, image recognition, and image detection, which can be useful in many real-world applications. In this study, we analyzed visual features of images to detect advertising images from scanned images of various magazines. The aim is to identify key features of advertising images and to apply them to real-world application. The proposed work will eventually help improve marketing strategies, which requires the classification of advertising images from magazines. We employed convolutional neural networks to classify scanned images as either advertisements or non-advertisements (i.e., articles). The results show that the proposed approach outperforms other classifiers and the related work in terms of accuracy.

Download Full-text