scholarly journals Image Denoising to enhance Character Recognition using Deep Learning

Author(s):  
Vanlal ruata ◽  
J. Hussain

Abstract In this paper, we proposed implementing a Deep Convolutional Neural Network. A relationship between a noisy character image to its clean counter-part are mapped using Deep Convolutional Neural Network.The overall process is divided into two stages: noise type classification and image denoising. Firstly, the noise type classification identifies the types of noise, and based on this noise type, a particular denoising model is selected, which increases the image denoising performance. The denoising network inputs a noisy image and a target of its clean corresponding image during the training. After the mapping function is trained, the generated model performs character image denoising. Then, on each band, a trained mapping function perform image denoising irrespective of the other band. Finally, each block is assembled to generate a clean image. In this paper, the MNIST and Char74K dataset of handwritten digits diluted with artificial noise divided into ten types are used for experimentation.. Our experimental results show that the proposed techniques perform better image denoising ascompared to the existing methods, both in terms of image noise type classification and image denoising. The overall Character recognition accuracy increased by 66% after performing the proposed denoising technique.

Perception ◽  
2021 ◽  
pp. 030100662110140
Author(s):  
Xingchen Zhou ◽  
A. M. Burton ◽  
Rob Jenkins

One of the best-known phenomena in face recognition is the other-race effect, the observation that own-race faces are better remembered than other-race faces. However, previous studies have not put the magnitude of other-race effect in the context of other influences on face recognition. Here, we compared the effects of (a) a race manipulation (own-race/other-race face) and (b) a familiarity manipulation (familiar/unfamiliar face) in a 2 × 2 factorial design. We found that the familiarity effect was several times larger than the race effect in all performance measures. However, participants expected race to have a larger effect on others than it actually did. Face recognition accuracy depends much more on whether you know the person’s face than whether you share the same race.


Author(s):  
Juan Luis Pérez-Ruiz ◽  
Igor Loboda ◽  
Iván González-Castillo ◽  
Víctor Manuel Pineda-Molina ◽  
Karen Anaid Rendón-Cortés ◽  
...  

The present paper compares the fault recognition capabilities of two gas turbine diagnostic approaches: data-driven and physics-based (a.k.a. gas path analysis, GPA). The comparison takes into consideration two differences between the approaches, the type of diagnostic space and diagnostic decision rule. To that end, two stages are proposed. In the first one, a data-driven approach with an artificial neural network (ANN) that recognizes faults in the space of measurement deviations is compared with a hybrid GPA approach that employs the same type of ANN to recognize faults in the space of estimated fault parameter. Different case studies for both anomaly detection and fault identification are proposed to evaluate the diagnostic spaces. They are formed by varying the classification, type of diagnostic analysis, and deviation noise scheme. In the second stage, the original GPA is reconstructed replacing the ANN with a tolerance-based rule to make diagnostic decisions. Here, two aspects are under analysis: the comparison of GPA classification rules and whole approaches. The results reveal that for simple classifications both spaces are equally accurate for anomaly detection and fault identification. However, for complex scenarios, the data-driven approach provides on average slightly better results for fault identification. The use of a hybrid GPA with ANN for a full classification instead of an original GPA with tolerance-based rule causes an increase of 12.49% in recognition accuracy for fault identification and up to 54.39% for anomaly detection. As for the whole approach comparison, the application of a data-driven approach instead of the original GPA can lead to an improvement of 12.14% and 53.26% in recognition accuracy for fault identification and anomaly detection, respectively.


2003 ◽  
Vol 14 (3) ◽  
pp. 147-152 ◽  
Author(s):  
Jaime Aparecido Cury ◽  
Aline Soler Marques ◽  
Cíntia Pereira Machado Tabchoury ◽  
Altair Antoninha Del Bel Cury

Since dental plaque reservoirs of fluoride (F), calcium (Ca) and inorganic phosphorus (Pi) are susceptible to decreases in pH, this in situ crossover study was conducted to test the hypothesis that the low concentration of these ions in plaque, formed in the presence of sucrose, could be attributed merely to the fermentation of this sugar. Eleven volunteers wore palatal appliances containing 6 human enamel blocks during two stages. In each stage, the treatments were either 20% sucrose solution or distilled deionized water, which were dripped onto the blocks 8 times a day. After 28 days, in each stage, the dental plaque formed on two blocks was collected, the treatment was inverted and after a further 24 and 48 h, the biofilm formed was collected from the other blocks. The concentration of acid-soluble F, Ca and Pi, and the concentration of insoluble polysaccharide (IP) were determined in the dental plaque. Statistically lower concentrations of F, Ca and Pi, and a higher concentration of IP were found in the 28-day biofilm formed in the presence of sucrose than in its absence; after the treatment inversion the change in F, Ca and Pi was not statistically significant, but the IP concentration changed significantly. The hypothesis was rejected because change in concentration of F, Ca and Pi is not due to fermentation of the sucrose.


Author(s):  
J.C. ANIGBOGU ◽  
A. BELAÏD

A multi-level multifont character recognition is presented. The system proceeds by first delimiting the context of the characters. As a way of enhancing system performance, typographical information is extracted and used for font identification before actual character recognition is performed. This has the advantage of sure character identification as well as text reproduction in its original form. The font identification is based on decision trees where the characters are automatically arranged differently in confusion classes according to the physical characteristics of fonts. The character recognizers are built around the first and second order hidden Markov models (HMM) as well as Euclidean distance measures. The HMMs use the Viterbi and the Extended Viterbi algorithms to which enhancements were made. Also present is a majority-vote system that polls the other systems for “advice” before deciding on the identity of a character. Among other things, this last system is shown to give better results than each of the other systems applied individually. The system finally uses combinations of stochastic and dictionary verification methods for word recognition and error-correction.


Electronics ◽  
2021 ◽  
Vol 10 (22) ◽  
pp. 2761
Author(s):  
Vaios Ampelakiotis ◽  
Isidoros Perikos ◽  
Ioannis Hatzilygeroudis ◽  
George Tsihrintzis

In this paper, we present a handwritten character recognition (HCR) system that aims to recognize first-order logic handwritten formulas and create editable text files of the recognized formulas. Dense feedforward neural networks (NNs) are utilized, and their performance is examined under various training conditions and methods. More specifically, after three training algorithms (backpropagation, resilient propagation and stochastic gradient descent) had been tested, we created and trained an NN with the stochastic gradient descent algorithm, optimized by the Adam update rule, which was proved to be the best, using a trainset of 16,750 handwritten image samples of 28 × 28 each and a testset of 7947 samples. The final accuracy achieved is 90.13%. The general methodology followed consists of two stages: the image processing and the NN design and training. Finally, an application has been created that implements the methodology and automatically recognizes handwritten logic formulas. An interesting feature of the application is that it allows for creating new, user-oriented training sets and parameter settings, and thus new NN models.


2022 ◽  
Vol 12 (2) ◽  
pp. 853
Author(s):  
Cheng-Jian Lin ◽  
Yu-Cheng Liu ◽  
Chin-Ling Lee

In this study, an automatic receipt recognition system (ARRS) is developed. First, a receipt is scanned for conversion into a high-resolution image. Receipt characters are automatically placed into two categories according to the receipt characteristics: printed and handwritten characters. Images of receipts with these characters are preprocessed separately. For handwritten characters, template matching and the fixed features of the receipts are used for text positioning, and projection is applied for character segmentation. Finally, a convolutional neural network is used for character recognition. For printed characters, a modified You Only Look Once (version 4) model (YOLOv4-s) executes precise text positioning and character recognition. The proposed YOLOv4-s model reduces downsampling, thereby enhancing small-object recognition. Finally, the system produces recognition results in a tax declaration format, which can upload to a tax declaration system. Experimental results revealed that the recognition accuracy of the proposed system was 80.93% for handwritten characters. Moreover, the YOLOv4-s model had a 99.39% accuracy rate for printed characters; only 33 characters were misjudged. The recognition accuracy of the YOLOv4-s model was higher than that of the traditional YOLOv4 model by 20.57%. Therefore, the proposed ARRS can considerably improve the efficiency of tax declaration, reduce labor costs, and simplify operating procedures.


2019 ◽  
Vol 10 (2) ◽  
pp. 277-288 ◽  
Author(s):  
Dewi Rawani ◽  
Ratu Ilma Indra Putri ◽  
Hapizah Hapizah

This research aims to produce a valid, practical, and having potential effects PISA-like mathematics problems using taekwondo context in Asian Games. The subjects were MIA 3 student of SMA 10 Palembang. This study was design research of development study in which had two stages: the preliminary and formative evaluation. The formative evaluation includes self-evaluation, one-to-one and expert review, small group, and field test. The context is used to have the students estimate maximum numbers of exercising athletes in a hall with a specific size. The result of the analysis shows that the problems which were reviewed by three expert reviews are valid qualitatively based on the PISA framework; it is also practical and easy to understand the problem. Based on the analysis of students’ answer, the developed problems display potential effects on student’s diverse basic mathematical abilities on the various process of answering the problems. The basic mathematics abilities emerging among which are reasoning and argument ability. It appears that students can develop and solve the problem by modeling using their assumptions. Also, the other ability is designing strategies to solve problems in which students use various procedures in solving problems leading the conclusion.


Author(s):  
Teddy Surya Gunawan ◽  
Abdul Mutholib ◽  
Mira Kartiwi

<span>Automatic Number Plate Recognition (ANPR) is an intelligent system which has the capability to recognize the character on vehicle number plate. Previous researches implemented ANPR system on personal computer (PC) with high resolution camera and high computational capability. On the other hand, not many researches have been conducted on the design and implementation of ANPR in smartphone platforms which has limited camera resolution and processing speed. In this paper, various steps to optimize ANPR, including pre-processing, segmentation, and optical character recognition (OCR) using artificial neural network (ANN) and template matching, were described. The proposed ANPR algorithm was based on Tesseract and Leptonica libraries. For comparison purpose, the template matching based OCR will be compared to ANN based OCR. Performance of the proposed algorithm was evaluated on the developed Malaysian number plates’ image database captured by smartphone’s camera. Results showed that the accuracy and processing time of the proposed algorithm using template matching was 97.5% and 1.13 seconds, respectively. On the other hand, the traditional algorithm using template matching only obtained 83.7% recognition rate with 0.98 second processing time. It shows that our proposed ANPR algorithm improved the recognition rate with negligible additional processing time.</span>


Author(s):  
John A. Taber

Two principal strains of ethical thought are evident in Indian religious and philosophical literature: one, central to Hinduism, emphasizes adherence to the established norms of ancient Indian culture, which are stated in the literature known as the Dharmaśāstras; another, found in texts of Buddhism, Jainism and Hinduism alike, stresses the renunciation of one’s familial and social obligations for the sake of attaining enlightenment or liberation from the cycle of rebirth. The Dharmaśāstras define in elaborate detail a way of life based on a division of society into four ‘orders’ (varṇas) – priests, warriors, tradesmen and servants or labourers – and, for the three highest orders, four ‘stages of life’ (āśramas). Renunciation is valid only in the final two stages of life, after one has fulfilled one’s responsibilities as a student of scripture and as a householder. The various traditions that stress liberation, on the other hand, advocate total, immediate commitment to the goal of liberation, for which the householder life presents insuperable distractions. Here, the duties of the householder are replaced by the practice of yoga and asceticism. Nevertheless, specific ethical observances are also recommended as prerequisites for the achievement of higher knowledge through yoga, in particular, nonviolence, truthfulness, not stealing, celibacy and poverty. The liberation traditions criticized the system of the Dharmaśāstras for being overly concerned with ritual and external forms of purity and condoning – indeed, prescribing – the killing of living beings in Vedic sacrifices; but it was only in the Dharmaśāstras that the notion of action solely for duty’s sake was appreciated. The Hindu scripture the Bhagavad Gītā (Song of God) represents an effort to synthesize the two ideals of renunciation and the fulfilment of obligation. It teaches that one should integrate yoga and action in the world. Only when acting out of the state of inner peace and detachment that is the culmination of the practice of yoga can one execute one’s duty without regard for the consequences of one’s actions. On the other hand, without the cultivation of inner yoga, the external forms of renunciation – celibacy, mendicancy, asceticism – are without significance. It is inner yoga that is the essence of renunciation, yet yoga is quite compatible with carrying out one’s obligations in the world.


SAGE Open ◽  
2018 ◽  
Vol 8 (4) ◽  
pp. 215824401881006
Author(s):  
Ching-Chih Liao

This article investigates the influence of the position of occlusion, structural composition, and design educational status on Chinese character recognition accuracy and response time. Tsao and Liao conducted an experiment using 18 of the 4,000 most commonly used Chinese characters and suggested that the primary and secondary recognition features of a “single-sided” occluded Chinese character are the key radical (or initial strokes) and the key component (i.e., combination of strokes), respectively. The study concluded that right-side occluded characters require a shorter response time and yield more accurate recognition and that educational background does not significantly affect recognition accuracy and response time. The present study considered the same 18 Chinese characters and extended the work of Tsao and Liao by exploring accuracy rate and response time in design and nondesign educational groups for the recognition of “double-sided” occluded Chinese characters. The experimental results indicated that right-side occlusion (including both bottom-right and top-right occlusion) requires a shorter response time and yields more accurate recognition than left-side occlusion. These results agree with those of Tsao and Liao, who found that the key radical of a Chinese character is its key visual recognition feature. Even double-sided occlusion of Chinese characters does not affect the recognition outcome if the position of occlusion does not blur the key radical. Moreover, the participants majoring in design recognized the occluded Chinese characters more slowly than those with no educational background in design.


Sign in / Sign up

Export Citation Format

Share Document