Image-Abstraction Framework as a Preprocessing Technique for Extraction of Text From Underexposed Complex Background and Graphical Embossing Images

2021 ◽  
Vol 13 (1) ◽  
pp. 1-35
Author(s):  
Pavan Kumar ◽  
Poornima B. ◽  
H. S. Nagendraswamy ◽  
C. Manjunath ◽  
B. E. Rangaswamy
Keyword(s):  
Image Quality Assessment ◽  
Text Documents ◽  
Complex Background ◽  
Average Accuracy ◽  
Assessment Techniques ◽  
Image Abstraction ◽  
Preprocessing Technique ◽  
Processing Techniques ◽  
Background Content ◽  
Traditional Image

Underexposed heterogeneous complex-background and graphical embossing text documents are treated using proposed preprocessing image-abstraction framework that can deliver the effective structure preserved abstracted output by manipulating visual-features from input images. Reading of the text character in such images is extremely poor; hence, the framework effectively boosted the significant image properties and quality features at every stage. Work effectively preserves the foreground structure of an image by comprehensively integrating the sequence of NPR filters and diminishes the background content of an image, and in this way, the framework contributes to separation of foreground text from image background. Effectiveness of the proposed work has been validated by conducting the trials on the selected dataset. In addition, user's visual-feedback and image quality assessment techniques were also used to evaluate the framework. Based on the obtained abstraction output, this work extracts text-character by wisely utilizing traditional image processing techniques with an average accuracy of 98.91%.

Structure Preserving Non-Photorealistic Rendering Framework for Image Abstraction and Stylization of Low-Illuminated and Underexposed Images

2021 ◽  
Vol 11 (2) ◽  
pp. 22-45
Author(s):  
Pavan Kumar ◽  
Poornima B. ◽  
Nagendraswamy H. S. ◽  
Manjunath C.
Keyword(s):  
Structural Features ◽  
Image Features ◽  
Visual Features ◽  
Structure Preserving ◽  
Photorealistic Rendering ◽  
Assessment Techniques ◽  
Contemporary Work ◽  
Image Abstraction ◽  
Future Work ◽  
Background Content

The proposed abstraction framework manipulates the visual-features from low-illuminated and underexposed images while retaining the prominent structural, medium scale details, tonal information, and suppresses the superfluous details like noise, complexity, and irregular gradient. The significant image features are refined at every stage of the work by comprehensively integrating a series of AnshuTMO and NPR filters through rigorous experiments. The work effectively preserves the structural features in the foreground of an image and diminishes the background content of an image. Effectiveness of the work has been validated by conducting experiments on the standard datasets such as Mould, Wang, and many other interesting datasets and the obtained results are compared with similar contemporary work cited in the literature. In addition, user visual feedback and the quality assessment techniques were used to evaluate the work. Image abstraction and stylization applications, constraints, challenges, and future work in the fields of NPR domain are also envisaged in this paper.

Detection of Blood-Related Diseases Using Deep Neural Nets

2019 ◽  
pp. 1-15
Author(s):  
Rajithkumar B. K. ◽  
Shilpa D. R. ◽  
Uma B. V.
Keyword(s):  
Image Processing ◽  
Biomedical Engineering ◽  
Medical Diagnosis ◽  
Blood Smear ◽  
Neural Nets ◽  
Laboratory Methods ◽  
Intelligent Algorithms ◽  
Image Processing Techniques ◽  
Processing Techniques ◽  
Traditional Image

Image processing offers medical diagnosis and it overcomes the shortcomings faced by traditional laboratory methods with the help of intelligent algorithms. It is also useful for remote quality control and consultations. As machine learning is stepping into biomedical engineering, there is a huge demand for devices which are intelligent and accurate enough to target the diseases. The platelet count in a blood sample can be done by extrapolating the number of platelets counted in the blood smear. Deep neural nets use multiple layers of filtering and automated feature extraction and detection and can overcome the hurdle of devising complex algorithms to extract features for each type of disease. So, this chapter deals with the usage of deep neural networks for the image classification and platelets count. The method of using deep neural nets has increased the accuracy of detecting the disease and greater efficiency compared to traditional image processing techniques. The method can be further expanded to other forms of diseases which can be detected through blood samples.

scholarly journals An Efficient Hemorrhage Detection System using Decision Tree Classifier

2019 ◽  
Vol 8 (3) ◽  
pp. 5728-5732
Keyword(s):  
Decision Tree ◽  
Active Contours ◽  
Detection System ◽  
Input Image ◽  
Morphological Operations ◽  
Decision Tree Classifier ◽  
Average Accuracy ◽  
Tree Classifier ◽  
Processing Techniques ◽  
Magnetic Resonant Imaging

the visual representations of the inner constituents of body along with the functions of either organs or tissues comprising its physiology are developed in medical imaging. These images can be obtained by various techniques such as computed tomography (CT), magnetic resonant imaging (MRI), and x-ray. The objective of the system mentioned in this paper is to detect the presence of hemorrhage and to classify the type of it when detected. CT images are considered here to find the hemorrhage. Pre-processing techniques such as grayscale conversion, image resizing, edge detection and sharpening are done to make the input image suitable for further processing. After preprocessing the images go through morphological operations to help identify the shape related features in correspondence to the hemorrhage. Sobel and markers are used in the processed ct image to highlight the interested region. Then watershed algorithm is employed for the purpose of segmentation. The presence of hemorrhage can be detected as a result of segmentation. Once hemorrhage is detected feature extraction is done to classify its type. Active contours are drawn and features extracted are fed to the decision tree. The classifier helps in finding the type of hemorrhage with the detected features. The classifier result can be viewed, interpreted and evaluated by medical assistance. The aim of this research is to increase the chance of predicting hemorrhage in the image and then to classify its type. The proposed system classifies three types of hemorrhages. The average accuracy of the system in classifying the three types of hemorrhage is found as 98%

scholarly journals Self-Organizing Map vs Initial Centroid Selection Optimization to Enhance K-Means with Genetic Algorithm to Cluster Transcribed Broadcast News Documents

2019 ◽  
Vol 17 (3) ◽  
pp. 316-324
Author(s):  
Ahmed Maghawry ◽  
Yasser Omar ◽  
Amr Badr
Keyword(s):  
Genetic Algorithm ◽  
Self Organizing Map ◽  
Optimal Solutions ◽  
Algorithm Optimization ◽  
Chi Square ◽  
Text Documents ◽  
Data Set ◽  
Average Accuracy ◽  
The Difference ◽  
Self Organizing

A compilation of artificial intelligence techniques are employed in this research to enhance the process of clustering transcribed text documents obtained from audio sources. Many clustering techniques suffer from drawbacks that may cause the algorithm to tend to sub optimal solutions, handling these drawbacks is essential to get better clustering results and avoid sub optimal solutions. The main target of our research is to enhance automatic topic clustering of transcribed speech documents, and examine the difference between implementing the K-means algorithm using our Initial Centroid Selection Optimization (ICSO) [16] with genetic algorithm optimization with Chi-square similarity measure to cluster a data set then use a self-organizing map to enhance the clustering process of the same data set, both techniques will be compared in terms of accuracy. The evaluation showed that using K-means with ICSO and genetic algorithm achieved the highest average accuracy.

Abstract 4408: Using a Large Electronic Medical Record to Validate 4q25 Variants Conferring Risk for Atrial Fibrillation

Circulation ◽  
2008 ◽  
Vol 118 (suppl_18) ◽  
Author(s):  
Joshua C Denny ◽  
Marylyn D Ritchie ◽  
Dana C Crawford ◽  
Andrea Havens ◽  
Justin Weiner ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Language Processing ◽  
Association Studies ◽  
Genomic Research ◽  
Genome Wide Association Studies ◽  
Nucleotide Polymorphisms ◽  
Heart Transplants ◽  
Text Documents ◽  
Research Populations ◽  
Processing Techniques

Background : Genome-wide association studies, largely in research populations, have identified susceptibility single-nucleotide polymorphisms (SNPs) for a broad range of human diseases, including variants at 4q25 associated with atrial fibrillation (AF). However, no studies have evaluated the applicability of these data to practice-based settings. Methods : This study was conducted in the Vanderbilt DNA Databank, a repository that accrues 500 –900 new samples/week from routine outpatient blood draws, and included 37,335 samples as of June 2, 2008. The Databank is linked to a de-identified derivative of the electronic medial record (EMR), which includes data for the last 15 years on 1.4 million subjects. We used natural language processing techniques and billing code queries to extract AF cases and controls without AF from the first 10,000 subjects entering the Databank. Cases had AF recorded in the cardiologist report of an electrocardiogram (ECG). Controls had at least one ECG and no AF, other abnormal atrial rhythms, or atrioventricular nodal ablation in any portion of the EMR, including text documents, billing codes, and ECGs. We excluded subjects with heart transplants and non-Caucasian ethnicity. Subjects were genotyped at rs2200733 and rs10033464, both located at 4q25, previously associated with AF with odds ratios (ORs) of 1.75 and 1.42, respectively. Results : We identified 168 cases with AF and 1695 controls. The electronic algorithms had an accuracy of 98% for identifying cases and 100% for controls over a random sample of 100 subjects each. The minor allele frequencies (MAF) for rs2200733 were 0.1419 for cases and 0.1032 for controls; the MAF for rs10033464 were 0.1019 for cases and 0.908 for controls. rs2200733 was significantly associated with AF (OR [95% confidence interval], 1.44 [1.01–2.03], p=0.04). The effect of rs10033464 on AF was not significant (OR, 1.14 [0.78 –1.67], p=0.52); however, power calculations indicate that 993 cases with AF were needed to replicate this effect. Conclusion : This practice-based study replicated an association identified in research datasets between a 4q25 SNP and AF. These findings support the utility of Electronic Medical Records coupled to DNA collections as resources for genomic research.

Identification of Abnormal Furnace Flame Based Image Processing

2014 ◽  
Vol 568-570 ◽  
pp. 763-767
Author(s):  
Hua Lei Cai ◽  
Kang Ling Fang
Keyword(s):  
Image Processing ◽  
Clustering Algorithm ◽  
Experimental Simulation ◽  
Design System ◽  
Image Processing Techniques ◽  
Point Position ◽  
Background Interference ◽  
Complex Background ◽  
Processing Techniques

Research using image processing techniques to identify new burning point of industrial tube furnace.First, get the flame image through the design system, and then using the symmetric differencing to obtain each furnace burning point position, and finally the use of Clustering Algorithm to identify the new burning point. Through the experimental simulation show that this algorithm can avoid the complex background interference in the furnace, accurate and effective identify the new burning point.

scholarly journals NO-REFERENCE IMAGE QUALITY MEASURE FOR IMAGES WITH MULTIPLE DISTORTIONS USING RANDOM FORESTS FOR MULTI METHOD FUSION

2018 ◽  
Vol 37 (2) ◽  
pp. 105 ◽  
Author(s):  
Kanjar De ◽  
Masilamani V
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Image Quality Assessment ◽  
Reference Image ◽  
Multiple Sources ◽  
Noise Image ◽  
Assessment Techniques ◽  
Image Quality Measure ◽  
Channel Errors

Over the years image quality assessment is one of the active area of research in image processing. Distortion in images can be caused by various sources like noise, blur, transmission channel errors, compression artifacts etc. Image distortions can occur during the image acquisition process (blur/noise), image compression (ringing and blocking artifacts) or during the transmission process. A single image can be distorted by multiple sources and assessing quality of such images is an extremely challenging task. The human visual system can easily identify image quality in such cases, but for a computer algorithm performing the task of quality assessment is a very difficult. In this paper, we propose a new no-reference image quality assessment for images corrupted by more than one type of distortions. The proposed technique is compared with the best-known framework for image quality assessment for multiply distorted images and standard state of the art Full reference and No-reference image quality assessment techniques available. 

Sign in / Sign up

Export Citation Format

Share Document