Extraction of Junctions, Lines and Regions of Irregular Line Drawing: The Chain Code Processing Algorithm

2012 ◽  
Author(s):  
Habibollah Haron ◽  
Dzulkifli Mohamed ◽  
Siti Mariyam Hj. Shamsuddin
Keyword(s):  
Feature Extraction ◽  
Key Words ◽  
Line Drawing ◽  
Engineering Product ◽  
Chain Code ◽  
Thinning Algorithm ◽  
Test Input ◽  
Code Algorithm ◽  
Regular Line ◽  
Thinning Process

Peringkat konsepsualisasi dalam kitar hayat reka bentuk produk kejuruteraan merupakan proses menterjemahkan idea jurutera ke atas sehelai kertas. Menggunakan sebatang pensil dan sehelai kertas, bentuk produk yang diinginkan akan dilakar. Lakaran seterusnya akan dikemaskinikan dengan menambah dimensi yang lebih tepat beserta pandangan-pandangan tambahan bagi menunjukkan kawasan terlindung. Kertas kerja ini membincangkan proses-proses yang terlibat dalam menterjemahkan lakaran berupa lukisan garisan tak sekata kepada lukisan sekata yang kemas. Proses ini juga turut menghasilkan tiga entiti penting iaitu simpang, garisan dan kawasan. Algoritma kod rantaian digunakan bagi mendapatkan entiti ini. Kertas kerja ini juga menerangkan proses penipisan yang terlibat sebelum algoritma kod rantaian dilaksanakan. Andaian-andaian, beberapa definisi penting dan kaedah memindahturun fail imej juga dipersembahkan. Kertas kerja ini diakhiri dengan beberapa lakaran input, kesimpulan dan cadangan pembaikan. Kata kunci: Terjemahan lukisan garisan; kod rantaian; pengestrakkan ciri; algoritma penipisan Conceptualization stage in designing engineering product is a process of translating engineer´s idea onto a sheet of paper. The product is always sketched on a sheet of paper using pencil. The sketch is tidied up by adding accurate dimension, and complete view of hidden part. This paper discusses part of the process involved in translating the sketch or irregular line drawing into a tidy or regular line drawing, that yield three important entities namely junction, line and region. The chain code algorithm is used to find these entities. The paper also explains explicit thinning process involved before the chain code methodology. Assumptions, important definitions and method of loading image file are also presented. The paper is concluded with several test input sketches, conclusion and future works. Key words: Line drawing; interpretation; chain code; feature extraction; thinning algorithm

Chain Code Algorithm in Deriving T–Junction and Region of a Freehand Sketch

2012 ◽  
Author(s):  
Habibollah Haron ◽  
Siti Mariyam Shamsuddin ◽  
Dzulkifli Mohamed
Keyword(s):  
Closed Loop ◽  
Line Drawing ◽  
Three Dimensional ◽  
Chain Code ◽  
Freehand Sketch ◽  
Code Algorithm ◽  
Picture Description ◽  
Loop Chain ◽  
Description Languages ◽  
Line Drawing Interpretation

Perwakilan kod rantai ialah salah satu daripada Bahasa Penghuraian Gambar yang digunakan untuk mewakili garisan. Kertas kerja ini menfokuskan kepada terjemahan lukisan garisan dengan menerapkan algoritma kod rantaai dalam mendapatkan dua entiti geometri, iaitu simpang–T dan kawasan, bagi lakaran lukisan garisan dua dimensi. Algoritma kod rantai tertutup ini mengandaikan bahawa lakaran mewakili objek padu tiga dimensi. Algoritma ini ialah berasaskan kod rantai Freeman 8–kaitan dalam tetingkap 3×3. Terdapat dua faktor yang menentukan kejayaan algoritma ini. Pertama ialah arah penjelajahan sama ada ikut jam atau lawan jam. Kedua ialah lokasi permulaan bagi penjelajahan dalam tetingkap 3×3 tersebut. Kertas kerja ini menerangkan faktor-faktor ini dan aplikasi mereka dalam mendapatkan entiti geometri tersebut. Perbincangan ini dibantu oleh contoh lakaran objek blok–L untuk memudahkan pemahaman terhadap algoritma. Kertas kerja ini diakhiri dengan kesimpulan dan cadangan pembaikan. Kata kunci: Terjemahan lukisan garisan, kod rantaian, objek blok-L, Bahasa Penghuraian Gambar Chain code scheme is one of the Picture Description Languages used to represent lines. This paper focuses on the line drawing interpretation by utilising closed loop chain code algorithm as a tool in deriving two geometric entities, i.e. T–junction and region, of a two–dimensional line drawing sketch. The closed loop chain code algorithm assumes that the sketch represents a three–dimensional solid object. The algorithm is based on 8–connected 3×3 windows of Freeman chain code. Two factors determine the success of the algorithm. The first factor is the direction of traverses either clockwise or anti–clockwise. The other is the start location of the 3×3 window traverse. This paper explains these factors and their applications in deriving the geometric entities. The discussion is supported with an example of L–block object for clarification in the presentation of the algorithm. This paper is concluded with conclusion and future works. Keywords: Line drawing interpretation, chain code, L-block object, Picture Description Languages

scholarly journals Object Feature Extraction of Songket Image Using Chain Code Algorithm

2017 ◽  
Vol 7 (1) ◽  
pp. 235 ◽  
Author(s):  
Yuhandri ◽  
Sarifuddin Madenda ◽  
Eri Prasetyo Wibowo ◽  
Karmilasari
Keyword(s):  
Feature Extraction ◽  
Chain Code ◽  
Code Algorithm ◽  
Object Feature

Penerbitan Maklumat Tiga Dimensi Sebuah Lukisan Garisan Menggunakan Kaedah Jumlah Kuasa Dua Terkecil

2012 ◽  
Author(s):  
Habibollah Haron ◽  
Dzulkifli Mohamed
Keyword(s):  
Linear System ◽  
Line Drawing ◽  
Least Square Method ◽  
Least Square ◽  
Geometric Information ◽  
Ordinary Least Square ◽  
Total Least Square ◽  
Regular Line ◽  
Space Image

Pengekstrakan lukisan garisan melibatkan proses menukar lukisan garisan tidak sekata kepada lukisan sekata, mendapatkan entiti asas simpang, garisan serta kawasan dan seterusnya mendapatkan maklumat tiga dimensi lukisan. Proses penukaran lukisan tidak sekata akan menghasilkan maklumat dua dimensi lukisan dan maklumat geometri dua dimensi lukisan iaitu simpang, garisan dan kawasan masing-masing yang mewakili unjuran bucu, pinggir dan permukaan dalam tiga dimensi. Berdasarkan maklumat geometri dua dimensi ini, jenis kenalaran imej ditentukan untuk membentuk set sistem linear lebih tentu. Grimstead menggunakan empat kenalaran imej dan menggunakan lelaran kuasa dua terkecil untuk menyelesaikan sistem linear lebih tentu yang dihasilkan. Kertas kerja ini akan mencadangkan kaedah jumlah kuasa dua terkecil untuk menyelesaikan sistem linear lebih tentu yang dibentuk oleh dua kenalaran imej. Perbandingan dengan kaedah Grimstead akan ditunjukkan dan penerangan akan dibantu oleh kes kajian dan paparan output. Kata kunci: Terjemahan garisan; Jumlah Kuasa Dua Terkecil; ruang gradien; kenalaran imej; sistem linear Line drawing interpretation involves process of converting irregular line drawing to regular line drawing. The converting process produces junctions, lines and regions that are two-dimensional projection of vertices, edges, and faces of a solid model respectively. Based on the geometric information obtained, image regularities are determined and a over-determined sets of linear systems is developed. Grimstead used the three image regularities in the linear system and iterative ordinary least square to solve them. The paper is intended to propose Total Least Square method in solving over-determined sets of linear system of image regularities of a line drawing. Two image regularities have been used. The solutions obtained are visualized with the help of MATLAB tool. Case study is given to assist the explaination. Key words: Line Interpretation; Total Least Square Method; Gradient Space; Image Regularities; Linear System

FREEMAN CHAIN CODE AS REPRESENTATION IN OFFLINE SIGNATURE VERIFICATION SYSTEM

2016 ◽  
Vol 78 (8-2) ◽  
Author(s):  
Aini Najwa Azmi ◽  
Dewi Nasien ◽  
Azurah Abu Samah
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Rejection Rate ◽  
Data Representation ◽  
Signature Verification ◽  
Global Features ◽  
Chain Code ◽  
Verification System ◽  
Offline Signature Verification ◽  
Handwritten Signature

Over recent years, there has been an explosive growth of interest in the pattern recognition. For example, handwritten signature is one of human biometric that can be used in many areas in terms of access control and security. However, handwritten signature is not a uniform characteristic such as fingerprint, iris or vein. It may change to several factors; mood, environment and age. Signature Verification System (SVS) is a part of pattern recognition that can be a solution for such situation. The system can be decomposed into three stages: data acquisition and preprocessing, feature extraction and verification. This paper presents techniques for SVS that uses Freeman chain code (FCC) as data representation. In the first part of feature extraction stage, the FCC was extracted by using boundary-based style on the largest contiguous part of the signature images. The extracted FCC was divided into four, eight or sixteen equal parts. In the second part of feature extraction, six global features were calculated. Finally, verification utilized k-Nearest Neighbour (k-NN) to test the performance. MCYT bimodal database was used in every stage in the system. Based on our systems, the best result achieved was False Rejection Rate (FRR) 14.67%, False Acceptance Rate (FAR) 15.83% and Equal Error Rate (EER) 0.43% with shortest computation, 7.53 seconds and 47 numbers of features.

scholarly journals A small-flowered natural Odontoglossum hybrid (Orchidaceae: Oncidiinae) from Ecuador

Lankesteriana ◽  
2019 ◽  
Author(s):  
Stig Dalström ◽  
Wesley E. Higgins
Keyword(s):  
Key Words ◽  
Line Drawing ◽  
Taxonomic Status ◽  
Parent Species ◽  
Natural Hybrid

A new small-flowered natural Odontoglossum hybrid from northwestern Ecuador is described and illustrated with a line drawing and a photograph. The novelty is compared with its sympatric parent species, Odontoglossum armatum and O. mirandum. The flower of the new natural hybrid has shorter erect lateral lip-lobes compared to those for O. mirandum, but distinctly longer erect lateral lip-lobes compared to those for O. armatum, which are basically lacking altogether. The taxonomic status of the variable O. mirandum is briefly discussed. Key words: Ecuador, new hybrid, Odontoglossum, Orchidaceae, Oncidiinae

scholarly journals A new small-flowered Cyrtochilum species (Orchidaceae: Oncidiinae) from the Condor mountains in Ecuador

Lankesteriana ◽  
2020 ◽  
Author(s):  
Stig Dalström ◽  
Wesley Higgins
Keyword(s):  
New Species ◽  
Key Words ◽  
Line Drawing ◽  
Morphological Features

A new small-flowered species of Cyrtochilum  from  the  isolated  range  of  the  Condor  mountains   in   Ecuador   is   described   and   illustrated   with   a   line   drawing   and   a   photograph   of   the   holotype.   It   shares   morphological  features  with  several  different-­looking  groups  of  Cyrtochilum,  such  as  the  two  generitypes  of   the  genus:  C.  undulatum  and C. flexuosum,  as  well  as  with  plants  in  the  C.  myanthum  complex.  These  groups   are   treated   as   three   separate   genera   by   some   (Cyrtochilum,   Trigonochilum   and  Dasyglossum, respectively),   but  the  combination  of  morphological  features  seen  in  our  new  species  brings  the  groups  together  into  one   polymorphic  but  genetically  monophyletic  genus. Key words:  Condor,  Cyrtochilum,  new  species,  Oncidiinae

A NEW THINNING ALGORITHM BASED ON CONTROLLED DELETION OF EDGE REGIONS

1993 ◽  
Vol 07 (05) ◽  
pp. 969-986 ◽  
Author(s):  
G. DIMAURO ◽  
S. IMPEDOVO ◽  
G. PIRLO
Keyword(s):  
Experimental Results ◽  
Thinning Algorithm ◽  
Structural Descriptions ◽  
Thinning Process

In this paper a new thinning algorithm for binary patterns is presented. The algorithm is based on an iterative controlled removal procedure working on entire regions of the pattern. The thinning process permits to obtain skeletons retaining important specificities of the pattern useful for robust structural descriptions. The experimental results carried out on typewritten and handwritten characters point out the efficacy of the algorithm with respect to other techniques in literature.

Analogizing the Thinning Algorithm and Elicitation of Vascular Landmark in Retinal Images

2016 ◽  
Vol 10 (3) ◽  
pp. 29-37
Author(s):  
Shiny Priyadarshini J. ◽  
Gladis D.
Keyword(s):  
Feature Extraction ◽  
Blood Vessel ◽  
Blood Vessels ◽  
Personal Identification ◽  
Retinal Images ◽  
Feature Points ◽  
Retinal Blood Vessel ◽  
Thinning Algorithm ◽  
Retinal Tissue ◽  
Unique Identity

The retinal tissue is composed of network of blood vessels forming a unique biometric pattern. Feature extraction in retinal blood vessel is becoming an emerging trend in the field of personal identification. Because of its unique identity and less vulnerability to noise and distortion it has become one of the most secured biometric identities. The paper highlights the segmentation of blood vessel and the extraction of feature points such as termination and bifurcation points using Zhang Suen's thinning algorithm in retinal images. A comparison has been made and results are analyzed and tabulated between Zhang Suen and Morphological thinning. The count has been taken for both termination and bifurcation markings as spurious and non- spurious minutiae. The spurious minutiae are removed by using the crossing number method. The results clearly depict that the Zhang Suen's thinning algorithm gives better result when compared to morphological thinning.

Sign in / Sign up

Export Citation Format

Share Document