A Study on Image Preprocessing to Improve the Recognition Rate of Convolutional Neural Networks

Skin cancers are one of the most common cancers in the world. Early detections and treatments of skin cancers can greatly improve the survival rates of patients. In this paper, a skin lesions classification system is developed with deep convolutional neural networks of ResNet50, which may help dermatologists to recognize skin cancers earlier. We utilize the ResNet50 as a pre-trained model. Then, by transfer learning, it is trained on our skin lesions dataset. Image preprocessing and dataset balancing methods are used to increase the accuracy of the classification model. In classification of skin diseases, our model achieves an overall accuracy of 83.74% on nine-class skin lesions. The experimental results show an impressive effect of the ResNet50 model in finegrained skin lesions classification and skin cancers recognition.

Download Full-text

Enhanced Intelligent Identification of Concrete Cracks Using Multi-Layered Image Preprocessing-Aided Convolutional Neural Networks

Sensors ◽

10.3390/s20072021 ◽

2020 ◽

Vol 20 (7) ◽

pp. 2021 ◽

Cited By ~ 1

Author(s):

Ronghua Fu ◽

Hao Xu ◽

Zijian Wang ◽

Lei Shen ◽

Maosen Cao ◽

...

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Concrete Surface ◽

Identification Accuracy ◽

Fine Tuning ◽

Crack Identification ◽

Image Preprocessing ◽

Promising Tool ◽

Concrete Crack ◽

Surface Images

Crack identification plays an essential role in the health diagnosis of various concrete structures. Among different intelligent algorithms, the convolutional neural networks (CNNs) has been demonstrated as a promising tool capable of efficiently identifying the existence and evolution of concrete cracks by adaptively recognizing crack features from a large amount of concrete surface images. However, the accuracy as well as the versatility of conventional CNNs in crack identification is largely limited, due to the influence of noise contained in the background of the concrete surface images. The noise originates from highly diverse sources, such as light spots, blurs, surface roughness/wear/stains. With the aim of enhancing the accuracy, noise immunity, and versatility of CNN-based crack identification methods, a framework of enhanced intelligent identification of concrete cracks is established in this study, based on a hybrid utilization of conventional CNNs with a multi-layered image preprocessing strategy (MLP), of which the key components are homomorphic filtering and the Otsu thresholding method. Relying on the comparison and fine-tuning of classic CNN structures, networks for detection of crack position and identification of crack type are built, trained, and tested, based on a dataset composed of a large number of concrete crack images. The effectiveness and efficiency of the proposed framework involving the MLP and the CNN in crack identification are examined by comparative studies, with and without the implementation of the MLP strategy. Crack identification accuracy subject to different sources and levels of noise influence is investigated.

Download Full-text

A Pointer Type Instrument Intelligent Reading System Design Based on Convolutional Neural Networks

Frontiers in Physics ◽

10.3389/fphy.2020.618917 ◽

2020 ◽

Vol 8 ◽

Author(s):

Yue Lin ◽

Qinghua Zhong ◽

Hailing Sun

Keyword(s):

Neural Networks ◽

Real Time ◽

Convolutional Neural Networks ◽

Feature Recognition ◽

Recognition Rate ◽

Recognition Algorithm ◽

Operating Conditions ◽

Automatic Identification ◽

Online Reading ◽

Reading System

The pointer instrument has the advantages of being simple, reliable, stable, easy to maintain, having strong anti-interference properties, and so on, which has long occupied the main position of electrical and electric instruments. Though the pointer instrument structure is simple, it is not convenient for real-time reading of measurements. In this paper, a RK3399 microcomputer was used for real-time intelligent reading of a pointer instrument using a camera. Firstly, a histogram normalization transform algorithm was used to optimize the brightness and enhance the contrast of images; then, the feature recognition algorithm You Only Look Once 3rd (YOLOv3) was used to detect and capture the panel area in images; and Convolutional Neural Networks were used to read and predict the characteristic images. Finally, predicted results were uploaded to a server. The system realized automatic identification, numerical reading, an intelligent online reading of pointer data, which has high feasibility and practical value. The experimental results show that the recognition rate of this system was 98.71% and the reading accuracy was 97.42%. What is more, the system can accurately locate the pointer-type instrument area and read corresponding values with simple operating conditions. This achievement meets the demand of real-time readings for analog instruments.

Download Full-text

Indian Classical Dance Action Identification and Classification with Convolutional Neural Networks

Advances in Multimedia ◽

10.1155/2018/5141402 ◽

2018 ◽

Vol 2018 ◽

pp. 1-10 ◽

Cited By ~ 5

Author(s):

P. V. V. Kishore ◽

K. V. V. Kumar ◽

E. Kiran Kumar ◽

A. S. C. S. Sastry ◽

M. Teja Kiran ◽

...

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Recognition Rate ◽

Human Action Recognition ◽

Human Action ◽

Action Identification ◽

Classical Dance ◽

Human Movements ◽

Indian Classical Dance

Extracting and recognizing complex human movements from unconstrained online/offline video sequence is a challenging task in computer vision. This paper proposes the classification of Indian classical dance actions using a powerful artificial intelligence tool: convolutional neural networks (CNN). In this work, human action recognition on Indian classical dance videos is performed on recordings from both offline (controlled recording) and online (live performances, YouTube) data. The offline data is created with ten different subjects performing 200 familiar dance mudras/poses from different Indian classical dance forms under various background environments. The online dance data is collected from YouTube for ten different subjects. Each dance pose is occupied for 60 frames or images in a video in both the cases. CNN training is performed with 8 different sample sizes, each consisting of multiple sets of subjects. The remaining 2 samples are used for testing the trained CNN. Different CNN architectures were designed and tested with our data to obtain a better accuracy in recognition. We achieved a 93.33% recognition rate compared to other classifier models reported on the same dataset.

Download Full-text

An efficient classification of flower images with convolutional neural networks

International Journal of Engineering & Technology ◽

10.14419/ijet.v7i1.1.9857 ◽

2017 ◽

Vol 7 (1.1) ◽

pp. 384 ◽

Cited By ~ 1

Author(s):

M V.D. Prasad ◽

B JwalaLakshmamma ◽

A Hari Chandana ◽

K Komali ◽

M V.N. Manoja ◽

...

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Neural Networks ◽

Convolutional Neural Networks ◽

Recognition Rate ◽

Image Data ◽

Image Database

Machine learning is penetrating most of the classification and recognition tasks performed by a computer. This paper proposes the classification of flower images using a powerful artificial intelligence tool, convolutional neural networks (CNN). A flower image database with 9500 images is considered for the experimentation. The entire database is sub categorized into 4. The CNN training is initiated in five batches and the testing is carried out on all the for datasets. Different CNN architectures were designed and tested with our flower image data to obtain better accuracy in recognition. Various pooling schemes were implemented to improve the classification rates. We achieved 97.78% recognition rate compared to other classifier models reported on the same dataset.

Download Full-text

Improved recognition rate of different material category using convolutional neural networks

Materials Today Proceedings ◽

10.1016/j.matpr.2021.04.307 ◽

2021 ◽

Author(s):

Abhay Shukla ◽

Gauri Kalnoor ◽

Amit Kumar ◽

N. Yuvaraj ◽

R. Manikandan ◽

...

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Recognition Rate

Download Full-text

Recognition of Handwritten Arabic and Hindi Numerals Using Convolutional Neural Networks

Applied Sciences ◽

10.3390/app11041573 ◽

2021 ◽

Vol 11 (4) ◽

pp. 1573

Author(s):

Amin Alqudah ◽

Ali Mohammad Alqudah ◽

Hiam Alquran ◽

Hussein R. Al-Zoubi ◽

Mohammed Al-Qodah ◽

...

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

High Performance ◽

Recognition Rate ◽

Second Stage ◽

The Past ◽

The World ◽

Very High ◽

Handwritten Arabic

Arabic and Hindi handwritten numeral detection and classification is one of the most popular fields in the automation research. It has many applications in different fields. Automatic detection and automatic classification of handwritten numerals have persistently received attention from researchers around the world due to the robotic revolution in the past decades. Therefore, many great efforts and contributions have been made to provide highly accurate detection and classification methodologies with high performance. In this paper, we propose a two-stage methodology for the detection and classification of Arabic and Hindi handwritten numerals. The classification was based on convolutional neural networks (CNNs). The first stage of the methodology is the detection of the input numeral to be either Arabic or Hindi. The second stage is to detect the input numeral according to the language it came from. The simulation results show very high performance; the recognition rate was close to 100%.

Download Full-text

A Novel Robust Classification Method for Ground-Based Clouds

Atmosphere ◽

10.3390/atmos12080999 ◽

2021 ◽

Vol 12 (8) ◽

pp. 999

Author(s):

Aihua Yu ◽

Ming Tang ◽

Gang Li ◽

Beiping Hou ◽

Zhongwei Xuan ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Feature Extraction ◽

Convolutional Neural Network ◽

Sparse Representation ◽

Convolutional Neural Networks ◽

Recognition Rate ◽

Classification Method ◽

Robust Classification ◽

Cloud Classification

Though the traditional convolutional neural network has a high recognition rate in cloud classification, it has poor robustness in cloud classification with occlusion. In this paper, we propose a novel scheme for cloud classification, in which the convolutional neural networks are used for feature extraction and a weighted sparse representation coding is adopted for classification. Three such algorithms are proposed. Experiments are carried out using the multimodal ground-based cloud dataset and the results show that in the case of occlusion, the accuracy of the proposed methods can be much improved over the traditional convolutional neural network-based algorithms.

Download Full-text

Forest fire image recognition based on convolutional neural network

Journal of Algorithms & Computational Technology ◽

10.1177/1748302619887689 ◽

2019 ◽

Vol 13 ◽

pp. 174830261988768 ◽

Cited By ~ 3

Author(s):

Yuanbin Wang ◽

Langfei Dang ◽

Jieying Ren

Keyword(s):

Neural Network ◽

Neural Networks ◽

Image Processing ◽

Convolutional Neural Network ◽

Convolutional Neural Networks ◽

Image Recognition ◽

Forest Fire ◽

Recognition Rate ◽

Extraction Process ◽

Fire Flame

In order to detect fire automatically, a forest fire image recognition method based on convolutional neural networks is proposed in this paper. There are two main types of fire recognition algorithms. One is based on traditional image processing technology and the other is based on convolutional neural network technology. The former is easy to lead in false detection because of blindness and randomness in the stage of feature selection, while for the latter the unprocessed convolutional neural network is applied directly, so that the characteristics learned by the network are not accurate enough, and recognition rate may be affected. In view of these problems, conventional image processing techniques and convolutional neural networks are combined, and an adaptive pooling approach is introduced. The fire flame area can be segmented and the characteristics can be learned by this algorithm ahead. At the same time, the blindness in the traditional feature extraction process is avoided, and the learning of invalid features in the convolutional neural network is also avoided. Experiments show that the convolutional neural network method based on adaptive pooling method has better performance and has higher recognition rate.

Download Full-text