An image segmentation algorithm using genetic strategy

Xiao, RuoHui

doi:10.1109/iccet.2010.5486029

Cited by 3 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The effect of image segmentation directly affects the performance of the target recognition. Some common segmentation algorithms contain Otsu segmentation algorithm [5][6][7], genetic algorithm [8], fuzzy C-means segmentation algorithm [9,10] and so on, but they also have certain limitations, for example, they only fit for the image which contains the fuzziness and the nondeterminacy, and they need much time for the calculation of the center pixel neighborhood.Documents [11][12][13] have provided some improvements for the traditional maximum entropy segmentation algorithm which has a range of shortcomings, such as the low calculation accuracy and the poor segmentation results, and they have acquired some good segmentation results. However, the two dimensional (2-D) maximum entropy algorithm assumes that the background region and object region occupy the most regions of the twodimensional histogram, and it ignores the impact of the boundary region information on the segmentation results, so in many situations the segmentation effect is not good.…”

Section: Introductionmentioning

confidence: 99%

A New Image Segmentation Algorithm and It’s Application in lettuce object segmentation

Sun¹,

Wang²,

Wu³

et al. 2012

TELKOMNIKA

View full text Add to dashboard Cite

AbstrakSegmentasi citra selada yang berdasarkan pengolahan citra komputer adalah premis dari pengujian kualitas selada non-destruktif. Algoritma entropi maksimum 2-D tradisional memiliki beberapa kesalahan, seperti akurasi segmentasi rendah, kecepatan lambat dan miskin kemampuan anti derau. Akibatnya, itu mengarah ke masalah segmentasi citra yang buruk dan efisiensi yang rendah. Suatu perbaikan algoritma entropi maksimum 2-D disajikan dalam makalah ini. Ini membagi daerah tersegmentasi dan lebih lanjut mengklasifikasikan pixel gambar tersegmentasi dengan metode entropi fuzzy minimum, dan mengurangi dampak titik derau, akibatnya akurasi segmentasi citra meningkat. Algoritma yang diperbaiki digunakan untuk segmentasi selada objek, dan hasil eksperimen menunjukkan bahwa peningkatan algoritma segmentasi memiliki banyak keunggulan dibandingkan dengan algoritma entropi maksimum 2-D tradisional, seperti berkurangnya interferensi palsu, kemampuan anti-derau yangkuat, ketahanan yang baik dan validitas . Kata kunci: entropi fuzzy maksimum yang rendah, entropi maksimum 2-D, kualitas selada, segmentasi gambar AbstractLettuce image segmentation which based on computer image processing is the premise of nondestructive testing of lettuce quality. The traditional 2-D maximum entropy algorithm has some faults, such as low accuracy of segmentation, slow speed, and poor anti-noise ability. As a result, it leads to the problems of poor image segmentation and low efficiency. An improved 2-D maximum entropy algorithm is presented in this paper. It redistricts segmented regions and furtherly classifies the segmented image pixels with the method of the minimum fuzzy entropy, and reduces the impact of noise points, as a result the image segmentation accuracy is improved. The improved algorithm is used to lettuce object segmentation, and the experimental results show that the improved segmentation algorithm has many advantages compared with the traditional 2-D maximum entropy algorithm, such as less false interference, strong anti-noise ability, good robustness and validity.

show abstract

Section: Introductionmentioning

confidence: 99%

A New Image Segmentation Algorithm and It’s Application in lettuce object segmentation

Sun¹,

Wang²,

Wu³

et al. 2012

TELKOMNIKA

View full text Add to dashboard Cite

show abstract

“…Some common segmentation algorithms contain Otsu segmentation algorithm [5][6][7], genetic algorithm [8], fuzzy C-means segmentation algorithm [9,10] and so on, but they also have certain limitations, for example, they only fit for the image which contains the fuzziness and the nondeterminacy, and they need much time for the calculation of the center pixel neighborhood.Documents [11][12][13] have provided some improvements for the traditional maximum entropy segmentation algorithm which has a range of shortcomings, such as the low calculation accuracy and the poor segmentation results, and they have acquired some good segmentation results. However, the two dimensional (2-D) maximum entropy algorithm assumes that the background region and object region occupy the most regions of the twodimensional histogram, and it ignores the impact of the boundary region information on the segmentation results, so in many situations the segmentation effect is not good.…”

Section: Introductionmentioning

confidence: 99%

A New Image Segmentation Algorithm and Its Application in Lettuce Object Segmentation

Sun

Wang

et al. 2012

TELKOMNIKA

View full text Add to dashboard Cite

show abstract

Optimization of Segmentation Quality of Integrated Circuit Images / Integrinių Grandynų Vaizdų Segmentavimo Kokybės Optimizavimas

Mušketas

2012

Mokslas - Lietuvos Ateitis

View full text Add to dashboard Cite

Sistema inzinerija, kompiuterii|technologija T120 System Engineering, Computer Technology T120 Elektronika ir elektrotechnika Electronics and Electrical Engineering INTEGRINiy GRANDYNy VAIZDIJ SEGMENTAVIMO KOKYBÉS OPTIMIZAVIMAS Gintautas Musketas Vilniaus Gedimino technikos universitetas El. pastas gintautas.musketas@vgtu.lt Santrauka. Nagrinéjamas genetiniii algoritmii taikymas integriniii grandynii aktyviiyii srièiii vaizdams segmentuoti. Teoriskai apraâomi taikomi segmentavimo metodai (morfologinis plétimas, erozija, pataikymo-nepataikymo transformacija, slenksöio fimkcija), genetiniai algoritmai. Vaizdo segmentavimas apibréèiamas kaip optimizavimo problema. Atliekamas eksperimentiäkai parinktos filtni sekos parametni optimizavimas ir parodoma, kad optimizuota filtni seka gaunami 6 % geresni rezultatai. ReikSminiai zodziai: optimizavimas, genetiniai algoritmai, integriniai gr£ind3'nai, vaizdo segmentavimas. © Vilniaus Gedimino technikos universitetas AbstractThe paper presents investigation into the application of genetic algorithms for the segmentation of the active regions of integrated circuit images. This article is dedicated to a theoretical examination of the applied methods (morphological dilation, erosion, hit-and-miss, threshold) and describes genetic algorithms, image segmentation as optimization problem. The genetic optimization of the predefined filter sequence parameters is carried out. Improvement to segmentation accuracy using a non optimized filter sequence makes 6%.

show abstract

An image segmentation algorithm using genetic strategy

Cited by 3 publications

References 10 publications

A New Image Segmentation Algorithm and It’s Application in lettuce object segmentation

A New Image Segmentation Algorithm and It’s Application in lettuce object segmentation

A New Image Segmentation Algorithm and Its Application in Lettuce Object Segmentation

Optimization of Segmentation Quality of Integrated Circuit Images / Integrinių Grandynų Vaizdų Segmentavimo Kokybės Optimizavimas

Contact Info

Product

Resources

About