Vehicle Classification Using Advanced Technologies

1996 ◽  
Vol 1551 (1) ◽  
pp. 45-50
Author(s):  
Chien-Hung Wei ◽  
Cheng-Chih Chang ◽  
Sheng-Shih Wang
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Research Process ◽  
Vehicle Classification ◽  
Ann Model ◽  
Traffic Pattern ◽  
Research Areas ◽  
Advanced Technologies ◽  
Potential Applications ◽  
Hidden Layer

Applying advanced technologies to existing problem domains is a highly desirable approach in many research areas. Among these techniques, image processing has been shown useful in transportation fields for such tasks as traffic pattern recognition, data collection, accident detection, and pavement evaluation. The integrated model with artificial neural networks (ANNs) has promising potential applications. The image processing and ANN model are combined to explore the feasibility of vehicle classification in real-world situations. Three methods were developed during the research process: ground segmentation, background subtraction, and window segmentation. The first two methods were used to separate the objects of scene and nonscene from the actual traffic image. To reduce the complexity of neural networks, the image was divided into 16 windows and three characteristics (occupation rates of vehicles, of horizontal image lines, and of vertical image lines) of each window were extracted to generate 48 factors as the input units of the neural network. The backpropagation ANN model with one hidden layer is employed. The experiments show that the accurate recognition rates of heavy vehicles, small cars, and motorcycles are 98.5, 96.92, and 91.94 percent, respectively. The result implies the remarkable applicability of the proposed methods in transportation areas.

scholarly journals Quality Improvement for Exemplar-based Image Inpainting using a Modified Searching Mechanism

2020 ◽  
Vol 4 (1) ◽  
pp. 1
Author(s):  
Mariwan Wahid Ahmed ◽  
Alan Anwer Abdulla
Keyword(s):  
Image Processing ◽  
Image Compression ◽  
Euclidean Distance ◽  
Image Inpainting ◽  
Input Image ◽  
Second Step ◽  
Research Areas ◽  
Potential Applications ◽  
Priority Function ◽  
Popular Images

Digital image processing has a significant impact in different research areas including medical image processing, biometrics, image inpainting, object detection, information hiding, and image compression. Image inpainting is a science of reconstructing damaged parts of digital images and filling-in regions in which information are missing which has many potential applications such as repairing scratched images, removing unwanted objects, filling missing area, and repairing old images. In this paper, an image inpainting algorithm is developed based on exemplar, which is one of the most important and popular images inpainting technique, to fill-in missing area that caused either by removing unwanted objects, by image compression, by scratching image, or by image transformation through internet. In general, image inpainting consists of two main steps: The first one is the priority function. In this step, the algorithm decides to select which patch has the highest priority to be filled at the first. The second step is the searching mechanism to find the most similar patch to the selected highest priority patch to be inpainted. This paper concerns the second step and an improved searching mechanism is proposed to select the most similar patch. The proposed approach entails three steps: (1) Euclidean distance is used to find the similarity between the highest priority patches which need to be inpainted with each patch of the input image, (2) the position/location distance between those two patches is calculated, and (3) the resulted value from the first step is summed with the resulted value obtained from the second step. These steps are repeated until the last patch from the input image is checked. Finally, the smallest distance value obtained in step 3 is selected as the most similar patch. Experimental results demonstrated that the proposed approach gained a higher quality in terms of both objectives and subjective compared to other existing algorithms.

scholarly journals Variance Reduction in Low Light Image Enhancement Model

2020 ◽  
Vol 9 (4) ◽  
pp. 139-142
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Image Processing ◽  
Image Enhancement ◽  
Variance Reduction ◽  
Low Light ◽  
Light Image ◽  
Hidden Layer

In image processing, enhancement of images taken in low light is considered to be a tricky and intricate process, especially for the images captured at nighttime. It is because various factors of the image such as contrast, sharpness and color coordination should be handled simultaneously and effectively. To reduce the blurs or noises on the low-light images, many papers have contributed by proposing different techniques. One such technique addresses this problem using a pipeline neural network. Due to some irregularity in the working of the pipeline neural networks model [1], a hidden layer is added to the model which results in a decrease in irregularity.

A MODIFIED ERROR BACKPROPAGATION ALGORITHM FOR COMPLEX-VALUE NEURAL NETWORKS

2005 ◽  
Vol 15 (06) ◽  
pp. 435-443 ◽  
Author(s):  
XIAOMING CHEN ◽  
ZHENG TANG ◽  
CATHERINE VARIAPPAN ◽  
SONGSONG LI ◽  
TOSHIMI OKADA
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Fourier Transformation ◽  
Error Function ◽  
Local Minima ◽  
Backpropagation Algorithm ◽  
Speed Up ◽  
Simulation Results ◽  
Hidden Layer ◽  
Complex Valued

The complex-valued backpropagation algorithm has been widely used in fields of dealing with telecommunications, speech recognition and image processing with Fourier transformation. However, the local minima problem usually occurs in the process of learning. To solve this problem and to speed up the learning process, we propose a modified error function by adding a term to the conventional error function, which is corresponding to the hidden layer error. The simulation results show that the proposed algorithm is capable of preventing the learning from sticking into the local minima and of speeding up the learning.

Fuzzy ART Neural Network Model for Automated Detection of Freeway Incidents

1998 ◽  
Vol 1634 (1) ◽  
pp. 56-63 ◽  
Author(s):  
Sherif S. Ishak ◽  
Haitham M. Al-Deek
Keyword(s):  
Neural Networks ◽  
False Alarm ◽  
False Alarm Rate ◽  
Back Propagation ◽  
Incident Detection ◽  
Traffic Patterns ◽  
Traffic Pattern ◽  
Detection Algorithms ◽  
Fuzzy Art ◽  
Freeway Incidents

Pattern recognition techniques such as artificial neural networks continue to offer potential solutions to many of the existing problems associated with freeway incident-detection algorithms. This study focuses on the application of Fuzzy ART neural networks to incident detection on freeways. Unlike back-propagation models, Fuzzy ART is capable of fast, stable learning of recognition categories. It is an incremental approach that has the potential for on-line implementation. Fuzzy ART is trained with traffic patterns that are represented by 30-s loop-detector data of occupancy, speed, or a combination of both. Traffic patterns observed at the incident time and location are mapped to a group of categories. Each incident category maps incidents with similar traffic pattern characteristics, which are affected by the type and severity of the incident and the prevailing traffic conditions. Detection rate and false alarm rate are used to measure the performance of the Fuzzy ART algorithm. To reduce the false alarm rate that results from occasional misclassification of traffic patterns, a persistence time period of 3 min was arbitrarily selected. The algorithm performance improves when the temporal size of traffic patterns increases from one to two 30-s periods for all traffic parameters. An interesting finding is that the speed patterns produced better results than did the occupancy patterns. However, when combined, occupancy–speed patterns produced the best results. When compared with California algorithms 7 and 8, the Fuzzy ART model produced better performance.

Algorithms for segmentation and recognition of objects on medical images based on chiarlet transformation and neural networks

2020 ◽  
pp. 35-45
Author(s):  
Y.A. Hamad ◽  
K.V. Simonov ◽  
A.S. Kents
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Computer Vision ◽  
Edge Detection ◽  
Medical Images ◽  
Classification Algorithms ◽  
Visual Data ◽  
Recognition Of Objects

The paper considers general approaches to image processing, analysis of visual data and computer vision. The main methods for detecting features and edges associated with these approaches are presented. A brief description of modern edge detection and classification algorithms suitable for isolating and characterizing the type of pathology in the lungs in medical images is also given.

Analysis of Non-Linear Activation Functions for Classification Tasks Using Convolutional Neural Networks

2019 ◽  
Vol 12 (3) ◽  
pp. 156-161 ◽  
Author(s):  
Aman Dureja ◽  
Payal Pahwa
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Activation Function ◽  
Primary Objective ◽  
Experimental Comparison ◽  
Activation Functions ◽  
Practical Applications ◽  
Network Activation ◽  
Non Linear ◽  
Hidden Layer

Background: In making the deep neural network, activation functions play an important role. But the choice of activation functions also affects the network in term of optimization and to retrieve the better results. Several activation functions have been introduced in machine learning for many practical applications. But which activation function should use at hidden layer of deep neural networks was not identified. Objective: The primary objective of this analysis was to describe which activation function must be used at hidden layers for deep neural networks to solve complex non-linear problems. Methods: The configuration for this comparative model was used by using the datasets of 2 classes (Cat/Dog). The number of Convolutional layer used in this network was 3 and the pooling layer was also introduced after each layer of CNN layer. The total of the dataset was divided into the two parts. The first 8000 images were mainly used for training the network and the next 2000 images were used for testing the network. Results: The experimental comparison was done by analyzing the network by taking different activation functions on each layer of CNN network. The validation error and accuracy on Cat/Dog dataset were analyzed using activation functions (ReLU, Tanh, Selu, PRelu, Elu) at number of hidden layers. Overall the Relu gave best performance with the validation loss at 25th Epoch 0.3912 and validation accuracy at 25th Epoch 0.8320. Conclusion: It is found that a CNN model with ReLU hidden layers (3 hidden layers here) gives best results and improve overall performance better in term of accuracy and speed. These advantages of ReLU in CNN at number of hidden layers are helpful to effectively and fast retrieval of images from the databases.

scholarly journals Hardware implementation of radial-basis neural networks with Gaussian activation functions on FPGA

2021 ◽  
Author(s):  
Volodymyr Shymkovych ◽  
Sergii Telenyk ◽  
Petro Kravets
Keyword(s):  
Neural Networks ◽  
Hardware Implementation ◽  
Gaussian Function ◽  
Activation Function ◽  
Rbf Neural Networks ◽  
Activation Functions ◽  
Rbf Network ◽  
Combination Scheme ◽  
Radial Basis ◽  
Hidden Layer

AbstractThis article introduces a method for realizing the Gaussian activation function of radial-basis (RBF) neural networks with their hardware implementation on field-programmable gaits area (FPGAs). The results of modeling of the Gaussian function on FPGA chips of different families have been presented. RBF neural networks of various topologies have been synthesized and investigated. The hardware component implemented by this algorithm is an RBF neural network with four neurons of the latent layer and one neuron with a sigmoid activation function on an FPGA using 16-bit numbers with a fixed point, which took 1193 logic matrix gate (LUTs—LookUpTable). Each hidden layer neuron of the RBF network is designed on an FPGA as a separate computing unit. The speed as a total delay of the combination scheme of the block RBF network was 101.579 ns. The implementation of the Gaussian activation functions of the hidden layer of the RBF network occupies 106 LUTs, and the speed of the Gaussian activation functions is 29.33 ns. The absolute error is ± 0.005. The Spartan 3 family of chips for modeling has been used to get these results. Modeling on chips of other series has been also introduced in the article. RBF neural networks of various topologies have been synthesized and investigated. Hardware implementation of RBF neural networks with such speed allows them to be used in real-time control systems for high-speed objects.

Sign in / Sign up

Export Citation Format

Share Document