Compressed residual-VGG16 CNN model for big data places image recognition

Qassim, Hussam; Verma, Abhishek; Feinzimer, David

doi:10.1109/ccwc.2018.8301729

Cited by 370 publications

(166 citation statements)

References 10 publications

Supporting

Mentioning

164

Contrasting

Unclassified

Order By: Relevance

“…When k = 6, the better accuracy obtained by set26 1,2 =6,000 is approach to the accuracy obtained by…”

Section: When Set23 5tmentioning

confidence: 73%

See 1 more Smart Citation

How Does the Data Set and the Number of Categories Affect CNN-based Image Classification Performance?

Luo¹,

Li²,

Yin³

et al. 2019

JSW

View full text Add to dashboard Cite

Convolution neural network(CNN) has been widely applied in many fields and achieved excellent results, especially in image classification tasks. As we all know, many factors affect the performance of image classification. In particular, the size of training data sets and the number of categories are important factors affecting performance. While for most people, a large number of training data set are difficult to obtain or need to do a classification task with a large number of categories. Thus, we consider two questions of this approach: How does the size of the data set affect performance? How does the number of categories affect performance? In order to figure out these two questions, we constructed two types of experiment: Experiment 1, changing the number of categories and exploring how the number of categories affects performance in image classification task. There are 7 groups experiment performed by increasing the number of categories and performed 5 times experiment in each group (35 times experiment in total). Observe the change in accuracy to analyze the impact of the number of categories on performance. Experiment 2, changing data set size and exploring how the data set size affect performance. For each k-classification experiment, we do 5 groups by increasing the size of the training set. There are 35 groups experiment performed 5 times experiment in each group (175 times experiment in total). Observe changes in accuracy to analyze the effect of data set size on performance. For the CNN-based network, the results of experiment 1 show that the more categories, the worse the performance, and the less categories, the better the performance. In addition, when the number of categories to be classified is large, sometimes better accuracy can be obtained. The results of experiment 2 show that the larger the training set, the higher the test accuracy. When the training data set are insufficient, better results can be obtained. Therefore, in classification experiment, when the data set size is small or the number of categories is large, we can do more experiments and retain the best results. Results of this paper not only can guide us to do experiments on image classification, but also have important guiding significance for other experiments based on deep learning.

show abstract

“…When k = 6, the better accuracy obtained by set26 1,2 =6,000 is approach to the accuracy obtained by…”

Section: When Set23 5tmentioning

confidence: 73%

“…Furthermore, analyzing 5 groups experiment results for each k-classification, we can know that when the training samples are insufficient, while sometimes better results can be obtained. For example, when k = 5, the better accuracy obtained by set25 1,5 =5,000 is approach to the accuracy obtained by 5 set25 2,3 =10,000.…”

Section: When Set23 5tmentioning

confidence: 83%

How Does the Data Set and the Number of Categories Affect CNN-based Image Classification Performance?

Luo¹,

Li²,

Yin³

et al. 2019

JSW

View full text Add to dashboard Cite

show abstract

“…The generated positive samples are shown in Figure 4. features [15]. Therefore, a CNN can easily misclassify roll marks due to their unfixed morphological features.…”

Section: Sample Amplification Of Roll Marksmentioning

confidence: 99%

Periodic Surface Defect Detection in Steel Plates Based on Deep Learning

Liu

2019

Applied Sciences

View full text Add to dashboard Cite

It is difficult to detect roll marks on hot-rolled steel plates as they have a low contrast in the images. A periodical defect detection method based on a convolutional neural network (CNN) and long short-term memory (LSTM) is proposed to detect periodic defects, such as roll marks, according to the strong time-sequenced characteristics of such defects. Firstly, the features of the defect image are extracted through a CNN network, and then the extracted feature vectors are inputted into an LSTM network for defect recognition. The experiment shows that the detection rate of this method is 81.9%, which is 10.2% higher than a CNN method. In order to make more accurate use of the previous information, the method is improved with the attention mechanism. The improved method specifies the importance of inputted information at each previous moment, and gives the quantitative weight according to the importance. The experiment shows that the detection rate of the improved method is increased to 86.2%.

show abstract

“…The final layer is the softmax layer. More details about the VGG16 architecture can be found in [14,24,25].…”

Section: Related Workmentioning

confidence: 99%

Classification of Genetically Identical Left and Right Irises Using a Convolutional Neural Network

Fang

Zhou

et al. 2019

Electronics

View full text Add to dashboard Cite

As one of the most reliable biometric identification techniques, iris recognition has focused on the differences in iris textures without considering the similarities. In this work, we investigate the correlation between the left and right irises of an individual using a VGG16 convolutional neural network. Experimental results with two independent iris datasets show that a remarkably high classification accuracy of larger than 94% can be achieved when identifying if two irises (left and right) are from the same or different individuals. This exciting finding suggests that the similarities between genetically identical irises that are indistinguishable using traditional Daugman’s approaches can be detected by deep learning. We expect this work will shed light on further studies on the correlation between irises and/or other biometric identifiers of genetically identical or related individuals, which would find potential applications in criminal investigations.

show abstract

Compressed residual-VGG16 CNN model for big data places image recognition

Cited by 370 publications

References 10 publications

How Does the Data Set and the Number of Categories Affect CNN-based Image Classification Performance?

How Does the Data Set and the Number of Categories Affect CNN-based Image Classification Performance?

Periodic Surface Defect Detection in Steel Plates Based on Deep Learning

Classification of Genetically Identical Left and Right Irises Using a Convolutional Neural Network

Contact Info

Product

Resources

About