scholarly journals CHARACTER IMAGE SEGMENTATION OF JAVANESE SCRIPT USING CONNECTED COMPONENT METHOD

2019 ◽  
Vol 12 (2) ◽  
pp. 67
Author(s):  
Yuna Sugianela ◽  
Nanik Suciati
Keyword(s):  
Image Segmentation ◽  
Character Recognition ◽  
Region Of Interest ◽  
Character Segmentation ◽  
Translation System ◽  
Important Process ◽  
Connected Component ◽  
Projection Profile ◽  
Centroid Distance ◽  
Meaningful Word

Automation of Javanese script translation is needed to make it easier for people to understand the meaning of ancient Javanese script. By using Javanese script image as input, the translation system generally consists of character segmentation, character recognition, and combining the recognized characters as a meaningful word. The segmentation which obtains region of interest of each character, is an important process in the translation system. In the previous research, segmentation using projection profile method can separate each character well. The method can overcome characters overlapping, but it still produces truncated characters. In this study, we proposed a new segmentation to reduce the truncated character. The first step of the proposed method is pre-processing that consists of converting input into binary image and cleaning noises. The next step is to determine the connected component labels, which further perform as candidate of characters. Some of the candidates are still represented by more than one labels, so that we need a process to merge the connected component labels that have centroid distance less than threshold. We evaluate the proposed method using Intersection over Union (IoU). The evaluation shows the best accuracy 93,26%.

scholarly journals Character Segmentation and Recognition of Marathi Language

2021 ◽  
Vol 9 (12) ◽  
pp. 1544-1551
Author(s):  
Saurabh Ravindra Nikam
Keyword(s):  
Image Segmentation ◽  
Character Recognition ◽  
Structural Features ◽  
Input Image ◽  
Character Segmentation ◽  
Important Process ◽  
Critical Task ◽  
The Individual ◽  
Segmentation Image

Abstract: In this paper Segmentation is one the most important process which decides the success of character recognition fashion. Segmentation is used to putrefy an image of a sequence of characters into sub images of individual symbols by segmenting lines and words. In segmentation image is partitioned into multiple corridor. With respect to the segmentation of handwritten words into characters it's a critical task because of complexity of structural features and kinds in writing styles. Due to this without segmentation these touching characters, it's delicate to fete the individual characters, hence arises the need for segmentation of touching characters in a word. Then we consider Marathi words and Marathi Numbers for segmentation. The algorithm is use for Segmentation of lines and also characters. The segmented characters are also stores in result variable. First it Separate the lines and also it Separate the characters from the input image. This procedure is repeated till end of train. Keywords: Image Segmentation, Handwritten Marathi Characters, Marathi Numbers, OCR.

scholarly journals Improvement of binarization performance using local otsu thresholding

2019 ◽  
Vol 9 (1) ◽  
pp. 264
Author(s):  
Khairun Saddami ◽  
Khairul Munadi ◽  
Yuwaldi Away ◽  
Fitri Arnia
Keyword(s):  
Character Recognition ◽  
Wiener Filter ◽  
Transformation Method ◽  
Wiener Filtering ◽  
Median Filtering ◽  
Important Process ◽  
Connected Component ◽  
Image Subtraction ◽  
Otsu Thresholding ◽  
Processing Steps

<p><span>Ancient document usually contains multiple noises such as uneven-background, show-through, water-spilling, spots, and blur text. The noise will affect the binarization process. Binarization is an extremely important process in image processing, especially for character recognition. This paper presents an improvement to Nina binarization technique. Improvements were achieved by reducing processing steps and replacing median filtering by Wiener filtering. First, the document background was approximated by using Wiener filter, and then image subtraction was applied. Furthermore, the manuscript contrast was adjusted by mapping intensity of image value using intensity transformation method. Next, the local Otsu thresholding was applied. For removing spotting noise, we applied labeled connected component. The proposed method had been testing on H-DIBCO 2014 and degraded Jawi handwritten ancient documents. It performed better regarding recall and precision values, as compared to Otsu, Niblack, Sauvola, Lu, Su, and Nina, especially in the documents with show-through, water-spilling and combination noises.</span></p>

scholarly journals Pengenalan Plat Nomor Polisi Kendaraan Bermotor

2012 ◽  
Vol 12 (1) ◽  
pp. 35
Author(s):  
Ottopianus Mellolo
Keyword(s):  
Image Processing ◽  
Digital Image ◽  
Character Recognition ◽  
Motor Vehicle ◽  
Region Of Interest ◽  
Base Plate ◽  
Character Segmentation ◽  
Test Image ◽  
Average Percentage ◽  
Plate Number

PENGENALAN PLAT NOMOR POLISI KENDARAAN BERMOTOR ABSTRAK Penelitian ini bertujuan membuat sistem yang dapat mengenali karakter pada plat nomor polisi kendaraan yang terdapat pada citra digital. Sampel yang digunakan sebanyak 50 citra uji terdiri atas 25 citra kendaraan pribadi dengan warna dasar plat hitam tulisan putih, 10 citra kendaraan dinas pemerintah dengan warna dasar plat merah tulisan putih, dan  15 citra angkutan umum dengan wara dasar plat kuning tulisan hitam. Adapun Penelitian ini dilakukan melalui beberapa tahap, yaitu (1) Pengolahan Citra, untuk mempersiapkan citra dan mengambil fitur – fitur penting yang akan digunakan pada tahap - tahap selanjutnya (2) Penentuan Region of Interest (ROI) yaitu penentuan posisi plat nomor dalam citra, (3) Segmentasi Karakter yaitu membagi citra plat nomor menjadi citra yang memuat satu karakter, dan (3) pengenalan karakter yaitu mencocokkan karakter yang dicari dengan karakter referensi untuk dikenali. Hasil penelitian menunjukkan bahwa sistem dapat mengenali karakter pada plat nomor polisi kendaraan bermotor untuk ketiga jenis plat nomor dengan persentase rata-rata sebesar 79,43%. Kata kunci: Citra, pengenalan, plat nomor polisi  MOTORIZED VEHICLE POLICE NUMBER PLATE RECOGNITION ABSTRACT` The research is aimed to create one system in recognize the characteristic of the motor vehicle plate number that has digital image. The number of samples used was 50 test image consisted of 25 private vehicle images with written white numbers on the black base plate, 10 govemment vehicle image with written white numbers on the red base plate and 15 public vehicle images with black written numbers on the yellow base plate. The research undenrwent several stages :( 1) Image processing to prepare image and get the important features to be used for next stages (2) Determining Region of Interest (ROl), determining plate position in image, (3) Character segmentation, dividing plate number image which can only accomodate one character ; and (4)Character recognition, character verification that is sought with reference character to be recognized. The results indicatet hat the system can recognize the characters on the motor vehicle police plate number for the three types of the plate numbers with the average percentage 79,43%. Keywords: Image, recognition, police plate number

Hijaiyah Letter Segmentation Using Connected Component Labeling Method

2020 ◽  
Vol 9 (2) ◽  
pp. 249
Author(s):  
Audini Nifira Putri ◽  
I Putu Gede Hendra Suputra
Keyword(s):  
Image Segmentation ◽  
Character Recognition ◽  
Euclidean Distance ◽  
Recognition System ◽  
Main Character ◽  
Connected Component ◽  
Connected Component Labeling ◽  
Segmentation Process ◽  
Labeling Method

Arabic letters or Hijaiyah letters recognition is a challenge in itself because one letter consists of more than one character, namely the main character, companion character such as dots and lines, and punctuation called harakat. The image segmentation process is the most important in a character recognition system because it affects the separation of objects in an image. In this research, Hijaiyah letter segmentation aims to separate the letters according to the character of each letter using the Connected Component Labeling (CCL) method. Merging labels on each character will be done by looking for the Euclidean distance value from adjacent centroids. The experiment succeeded in segmenting each Hijaiyah character with an accuracy value of 86%. 

scholarly journals Character Segmentation Of Degraded Odia Script

2020 ◽  
Vol 8 (2) ◽  
Author(s):  
Ipsita Pattnaik ◽  
Tushar Patnaik
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
West Bengal ◽  
Input Image ◽  
Character Segmentation ◽  
Vertical Projection ◽  
Projection Profile ◽  
Regional Language ◽  
Optical Character ◽  
Line Segmentation

Optical Character Recognition (OCR) is a field which converts printed text into computer understandable format that is editable in nature. Odia is a regional language used in Odisha, West Bengal & Jharkhand. It is used by over forty million people and still counting. With such large dependency on a language makes it important, to preserve its script, get a digital editable version of odia script. We propose a framework that takes computer printed odia script image as an input & gives a computer readable & user editable format of same, which eventually recognizes the characters printed in input image. The system uses various techniques to improve the image & perform Line segmentation followed by word segmentation & finally character segmentation using horizontal & vertical projection profile.

Character Segmentation to the Case Study Image of Quadratic Equation Expression

2020 ◽  
Vol 8 (3) ◽  
pp. 285
Author(s):  
Putu Indah Pradnyawati ◽  
I Gede Arta Wibawa
Keyword(s):  
Image Segmentation ◽  
Structural Analysis ◽  
Quadratic Equation ◽  
Character Segmentation ◽  
Connected Component ◽  
Quadratic Equations ◽  
Connected Component Labeling ◽  
Mathematical Expressions ◽  
Basic Numbers

The introduction of digital mathematical expressions can be said to be unusual because mathematical expressions consist of various symbols. The introduction of mathematical expressions can be divided into two main steps, namely the introduction of symbols and structural analysis. Segmentation of an image is an important part in the recognition of handwritten mathematical expressions, because segmentation is the first step of the recognition process. In this study, we will present the process of handwriting image segmentation for mathematical expressions in the form of quadratic equations using the Connected Component Labeling (CCL) method. From the results of the research conducted, it can be concluded that the segmentation process has succeeded in segmenting the handwritten images of mathematical expressions in the form of quadratic equations by producing the characters (compound characters) that make up mathematical expressions and grouping the ranks and basic numbers of quadratic equations.

scholarly journals Pengenalan Karakter Plat Nomor Mobil Secara Real Time

2013 ◽  
Vol 7 (1) ◽  
pp. 35
Author(s):  
Ikhwan Ruslianto ◽  
Agus Harjoko
Keyword(s):  
Success Rate ◽  
Real Time ◽  
Character Recognition ◽  
Template Matching ◽  
Component Analysis ◽  
Recognition System ◽  
Character Segmentation ◽  
Connected Component ◽  
Connected Component Analysis ◽  
Complex Background

AbstrakPengenalan plat nomor di Indonesia biasanya digunakan pada sistem parkir yang masih dilakukan secara manual, yaitu dengan mencatat karakter plat nomor oleh petugas jaga parkir. Padahal pengenalan plat nomor tidak hanya dilakukan untuk system perparkiran tetapi dapat digunakan untuk menemukan kendaraan yang melanggar peraturan lalu lintas dijalan raya secara real time, misalnya pelaku tabrak lari pada kecelakaan maupun kendaraan yang melanggar rambu-rambu lalu lintas.Penelitian ini memberikan alternatif pengenalan karakter plat nomor mobil menggunakan metode connected component analysis dan matching sehingga dapat menyelesaikan permasalahan dengan background yang kompleks dan mobil yang bergerak dijalan raya.Metode connected component analysis berhasil melakukan proses segmentasi plat dan segmentasi karakter dengan kondisi background yang kompleks secara tepat terhadap 67 sampel citra dengan tingkat keberhasilan 95,52% untuk segmentasi plat dan 94,98% untuk segmentasi karakter dan metode template matching berhasil melakukan proses pengenalan karakter secara akurat dengan tingkat keberhasilan 87,45%. Kata kunci— real time, connected component analysis, template matching  Abstract Indonesia’s number plat recognition system are typically used in parking lots that are still done manually, by recording the license plate characters by parking guard. Though number plate recognition system is not only for parking but can be used to find vehicles that violate traffic rules highway street in real time, such as actors on the hit and run accident and the vehicles that violate traffic signs.This study provides an alternative car number plate character recognition using connected component analysis and matching so as to solve problems with complex background and a moving car on the road.Connected component analysis method successfully to the plates segmentation and character segmentation in complex background condition are appropriate to the 67 sample images with the success rate of 95.52% for the plate segmentation and 94.98% for plate character segmentation and template matching method successfully perform the character recognition process accurately with a success rate of 87.45%. Keywords— real time, connected component analysis, template matching

scholarly journals Region-of-Interest-Based Cardiac Image Segmentation with Deep Learning

2021 ◽  
Vol 11 (4) ◽  
pp. 1965
Author(s):  
Raul-Ronald Galea ◽  
Laura Diosan ◽  
Anca Andreica ◽  
Loredana Popa ◽  
Simona Manole ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
Diagnostic System ◽  
Region Of Interest ◽  
General Purpose ◽  
Medical Image Segmentation ◽  
Dice Similarity Coefficient ◽  
Learning Methods ◽  
Study Results ◽  
Whole Heart

Despite the promising results obtained by deep learning methods in the field of medical image segmentation, lack of sufficient data always hinders performance to a certain degree. In this work, we explore the feasibility of applying deep learning methods on a pilot dataset. We present a simple and practical approach to perform segmentation in a 2D, slice-by-slice manner, based on region of interest (ROI) localization, applying an optimized training regime to improve segmentation performance from regions of interest. We start from two popular segmentation networks, the preferred model for medical segmentation, U-Net, and a general-purpose model, DeepLabV3+. Furthermore, we show that ensembling of these two fundamentally different architectures brings constant benefits by testing our approach on two different datasets, the publicly available ACDC challenge, and the imATFIB dataset from our in-house conducted clinical study. Results on the imATFIB dataset show that the proposed approach performs well with the provided training volumes, achieving an average Dice Similarity Coefficient of the whole heart of 89.89% on the validation set. Moreover, our algorithm achieved a mean Dice value of 91.87% on the ACDC validation, being comparable to the second best-performing approach on the challenge. Our approach provides an opportunity to serve as a building block of a computer-aided diagnostic system in a clinical setting.

Application of Image Processing to the Vehicle License Plate Recognition

2013 ◽  
Vol 760-762 ◽  
pp. 1638-1641 ◽  
Author(s):  
Chun Yu Chen ◽  
Bao Zhi Cheng ◽  
Xin Chen ◽  
Fu Cheng Wang ◽  
Chen Zhang
Keyword(s):  
Traffic Engineering ◽  
Character Recognition ◽  
Character Segmentation ◽  
License Plate ◽  
License Plate Recognition ◽  
Edge Extraction ◽  
Recognition Method ◽  
License Plate Location ◽  
Vehicle License Plate Recognition ◽  
Plate Location

At present, the traffic engineering and automation have developed, and the vehicle license plate recognition technology need get a corresponding improvement also. In case of identifying a car license picture, the principle of automatic license plate recognition is illustrated in this paper, and the processing is described in detail which includes the pre-processing, the edge extraction, the license plate location, the character segmentation, the character recognition. The program implementing recognition is edited by Matlab. The example result shows that the recognition method is feasible, and it can be put into practice.

Sign in / Sign up

Export Citation Format

Share Document