Research on recognition of coal and gangue based on image processing

2015 ◽  
Vol 12 (3) ◽  
pp. 247-254 ◽  
Author(s):  
Lihong Li ◽  
Haijiang Wang ◽  
Lei An
Keyword(s):  
Image Processing ◽  
Texture Analysis ◽  
Spatial Information ◽  
Texture Feature ◽  
Window Size ◽  
Mean Value ◽  
Adaptive Window ◽  
Gray Histogram ◽  
New Ideas ◽  
Novel Method

In order to avoid the waste of water resources and environmental pollution caused by separating coal and gangue in the traditional methods, a novel method based on image processing is proposed in this paper. Firstly the image of coal or gangue is preprocessed. Then the mean value of gray histogram is extracted which serves as the statistical feature value to initially recognize coal and gangue. Then the textural feature is extracted from the image which is based on an adaptive window of texture analysis. The adaptive window size is determined by the contrast texture feature parameter. The adaptive window of texture analysis can improve the discriminability of coal and gangue. This method not only considers the image’s gray feature but also utilizes the image’s spatial information, so the recognition precision is improved. This method provides new ideas for dry separation technology.

scholarly journals UNSUPERVISED TEXTURE CLASSIFICATION OF ENTROPY BASED LOCAL DESCRIPTOR USING K-MEANS CLUSTERING ALGORITHM

2011 ◽  
pp. 133-140 ◽  
Author(s):  
S. S. Sreeja Mole ◽  
L. Ganesan
Keyword(s):  
Texture Analysis ◽  
Clustering Algorithm ◽  
Spatial Information ◽  
Texture Classification ◽  
Clustering Algorithms ◽  
Texture Feature ◽  
Texture Features ◽  
Local Descriptor ◽  
Descriptor Approach

This paper presents an efficient approach for unsupervised Texture Segmentation and Classification, based on features extracted from entropy based local descriptor using K-means clustering with spatial information. The K- means clustering algorithm is commonly used in computer vision as a form of image segmentation. Texture analysis refers to a class of mathematical procedures and models that characterizes the spatial variations within imagery as a means of extracting information. Texture analysis may require the solution of two different problems first is Segmentation and Classification of a given image according to the different texture and second was for of a given texture with respect to a set of known textures. Based on the proposed concept, this paper describes the entropy based local descriptor using K-Means with spatial information approach. Experimental results show that the proposed framework performs very well compared to other clustering algorithms in all measured criteria. Spatial information has been effectively used for unsupervised texture classification for Brodatz of texture images. The model is not specifically confined to a particular texture feature. We tested this algorithm using other texture features. The proposed entropy based local descriptor approach gives good accuracy when compared with other methods.

Comparison of Different Image Processing Methods with Spatial Information in Clinical Brain MRI

2020 ◽  
Author(s):  
Iza Sazanita Isa ◽  
Mohamad Khairul Faizi Mat Saad ◽  
Muhammad Haris Khusairi Mohmad Kadir ◽  
Ahmad Afifi Ahmad Afandi ◽  
Noor Khairiah A. Karim ◽  
...  
Keyword(s):  
Image Processing ◽  
Spatial Information ◽  
Brain Mri ◽  
Processing Methods

scholarly journals Predict Growth Stages of Wheat Crop using Digital Image Processing

2020 ◽  
Vol 8 (5) ◽  
pp. 3026-3035
Keyword(s):  
Image Processing ◽  
Digital Image Processing ◽  
Digital Image ◽  
Processing Technique ◽  
Mean Value ◽  
Image Processing Technique ◽  
Wheat Crop ◽  
Growth Stages ◽  
Increase Productivity ◽  
Crop Growth Stages

Manual examination is not as accurate to examine crop growing stages because of the possibility of the human mistake and errors. While machine examination or automatic examination can easily examine crop growing stages and increase productivity because it provides fast and accurate examine result. This study provide a solution to finding the wheat crop growth stages, Once the growing stages are established, farmers can take suitable and measured steps to improve the production of wheat or other agricultural crops. For finding the growth stages of wheat digital image processing technique is used. RGB model, HSI model, mean value of green colour, hue and saturation images use for examining wheat crop.

scholarly journals Design and Implementation of a Student Archive Retrieval Method Based on Image Processing

2020 ◽  
Vol 34 (4) ◽  
pp. 487-494
Author(s):  
Lei An ◽  
Aihua Li
Keyword(s):  
Image Processing ◽  
Information Management ◽  
Image Feature ◽  
Similarity Measurement ◽  
Function Learning ◽  
Retrieval Method ◽  
Design And Implementation ◽  
Network Modules ◽  
Novel Method ◽  
Effectiveness And Efficiency

Compared with traditional manual archive organization and review, the student archive management system can manage massive student archives in a refined, regular, and scientific manner. The effectiveness and efficiency of the retrieval method directly bears on the utilization effect of student archives. Based on image processing, this paper puts forward a novel method for student archive retrieval, which greatly improves the classification, recognition, and information management of images in student archives during the retrieval. Firstly, a framework of student archive retrieval was introduced based on image processing. Next, a deep convolutional neural network (DCNN) was constructed for hash learning, and the functions of the three network modules were detailed, including image feature extraction, hash function learning, and similarity measurement. Finally, several indices were selected to evaluate the retrieval effect of student archives. The proposed method was proved effective and feasible through contrastive experiments. The research results provide a theoretical reference for the application of our method in other fields of image retrieval.

Brain Tumour Texture Analysis-A Method

2021 ◽  
Vol 4 (4) ◽  
Author(s):  
Samir Kumar Bandyopadhyay
Keyword(s):  
Image Processing ◽  
Brain Tumor ◽  
Texture Analysis ◽  
Brain Tumour ◽  
Tumor Segmentation ◽  
Biomedical Image Processing ◽  
Biomedical Analysis ◽  
Brain Tumor Segmentation ◽  
Human Brain Tumor ◽  
Biomedical Image

Computer aided technology is used in biomedical image processing. In biomedical analysis features are extracted and then the proposed method will detect any abnormalities present or not in the system to be considered. In recent days the detection of brain tumour through image processing is made in medical diagnosis. The separation of tumor is made by the process of segmentation. Brain in human is the most complicated and delicate anatomical structure. There are various brain ailments in human but the indication of cancer in brain tumour may be fatal for the human. Brain tumor can be malignant or benign. The neurologist or neurosurgeon wants to know the exact location, size, shape and texture of tumor from Magnetic Resonance Imaging (MRI) of brain before going to the operation of the brain tumour or decided whether operation of removing brain tumour is at all necessary or not. The disease is analyzed since operation may cause death to the patient. Initially they took a chance by prescribing medicines to see whether there is any improvement of the condition of the patient. If the result is not satisfactory then there is no option other than operation of the tumor. Doctors also take an attempt to find the texture of the tumor since it may help them to know the progress of the tumour. In addition to Brain tumor segmentation, the detection of surface of the texture of brain tumor is required for proper treatment. The chapter proposed methods for detection of the progressive nature of the texture in the tumor presence in brain. For this process segmentation of tumor from other parts of brain is essential. In the chapter segmentation techniques are presented before the texture analysis process is given. Finally, comparisons of the proposed method with other methods are analyzed.

Image Processing for Fruit Shape and Texture Feature Extraction - Review

2015 ◽  
Vol 129 (8) ◽  
pp. 30-33
Author(s):  
Trupen Meruliya ◽  
Parth Dhameliya ◽  
Jainish Patel ◽  
Dilav Panchal ◽  
Pooja Kadam ◽  
...  
Keyword(s):  
Image Processing ◽  
Feature Extraction ◽  
Texture Feature ◽  
Fruit Shape ◽  
Texture Feature Extraction
Sign in / Sign up

Export Citation Format

Share Document