Comparison of Segmentation Framework on Digital Microscope Images for Acute Lymphoblastic Leukemia Diagnosis Using RGB and HSV Color Spaces

ElDahshan, Kamal A.; Youssef, Mohamed S.; Masameer, Emad; Hassan, Mohammed

doi:10.14738/jbemi.22.1065

Cited by 16 publications

(15 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…After cropping and resizing the image, there was a shadow on white paper so that the background and foreground separation stage was needed. The aim was to keep the foreground colored Red Green Blue (RGB) and the background colored white [7][8].…”

Section: A Image Preprocessingmentioning

confidence: 99%

Classification Of Plants And Weeds In Multi-Leaf Image With Support Vector Machine Based On Leaves Shape And Texture Features

Meirista¹,

Mukhlash²,

Setiyono³

et al. 2018

Proceedings of the International Conference on Science and Technology (ICST 2018)

View full text Add to dashboard Cite

We often find plants that have similarities in terms of shape and texture. In agriculture if we want to plant a plant species, other plants will be called weeds as they can inhibit plant growth. We can easily classify plants and weeds using image processing. Watermelon plants were the objects of this research, so other plants besides watermelons will be considered weeds. The recognition of plants based on the similarity of the plant leaves used digital imagery which was divided into three stages. At the first stage, preprocessing was done by cropping the image, resizing the image, separating the background and foreground, and doing edge detection segmentation using the Canny operator. The second stage was feature extraction to retrieve important information for leaf recognition. The features used were features of shape and texture. Then we classified the leaves as leafy plants and weeds using the algorithm of Support Vector Machine (SVM). The SVM method is proven to have good accuracy for classifying plants and weeds based on the shape and texture features in a multi-leaf image using quadratic kernel. The average accuracy is 73.95%. Keywords-Classification of plants and weeds, Leaves shape and texture features, Multi-leaf image.

show abstract

Section: A Image Preprocessingmentioning

confidence: 99%

Classification Of Plants And Weeds In Multi-Leaf Image With Support Vector Machine Based On Leaves Shape And Texture Features

Meirista¹,

Mukhlash²,

Setiyono³

et al. 2018

Proceedings of the International Conference on Science and Technology (ICST 2018)

View full text Add to dashboard Cite

show abstract

“…Local contrast stretching (LCS) and median filter are applied on original acute lymphoblastic leukaemia image [3,4]. Otsu's global thresholding method is used to automatically perform histogram shape-based image thresholding [2,3].…”

Section: Introductionmentioning

confidence: 99%

“…A differentiation between using HSI and RGB color space to segment ALL is reported in [3]. Segmentation based on HSI color space was chosen as it produced the highest ALL segmentation rate.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study of White Blood cells Segmentation using Otsu Threshold and Watershed Transformation

Salem

Sobhy

Dosoky

2016

JBEMi

View full text Add to dashboard Cite

The aim of white blood cells (WBC) segmentation is to separate leukocytes from other different components in the blood peripheral image. In this paper, a method to segment white blood cells from microscopic images is proposed. The proposed method consists of three stages; Pre-processing, segmentation, and finally post-processing. In the pre-processing step; the color correction is used to enhance the image. In the segmentation step; two techniques have been used which are Otsu threshold and watershed marker-controlled followed by feature extraction. Shape features are used to differentiate between single and grouped cells. Artifacts are removed in the post-processing step. Experimental results show that the accuracy is 99.3% and 93.3% for the watershed based and the Otsu threshold based methods respectively. Experiments demonstrate that watershed marker-controlled outperforms Otsu threshold in the segmentation of WBC.

show abstract

“…Also, algorithm based on HSI color space is proposed in [12]. Based on HSV color space, segmentation technique [13] for ALL images is proposed.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Implementation of Acute Lymphoblastic Leukemia Images segmentation on the FPGA

ElDahshan

Youssef

Masameer

et al. 2015

AIVP

Self Cite

View full text Add to dashboard Cite

In the medical field, image segmentation process is considered the most essential step in image analysis. In this work, the color segmentation for acute lymphoblastic leukemia images (ALL) is applied to segment each leukemia image into two clearly defined regions: blasts and background. The ALL segmentation process is based on hue channel (H) of HSV color space as a method in segmentation of WBC from its complicated background. This work presents an efficient framework for segmentation of ALL images on a reconfigurable logic platform using Simulink, MATLAB and Xilinx System Generator (XSG). This segmentation framework is implemented on a FPGA using basic Xilinx Blockset to minimize hardware resources and lower execution time to be suitable enough for medical applications. It is designed using XSG as DSP design tool that enables the use of Simulink models, implemented in VHDL and synthesized for three different Xilinx FPGA boards.

show abstract

Comparison of Segmentation Framework on Digital Microscope Images for Acute Lymphoblastic Leukemia Diagnosis Using RGB and HSV Color Spaces

Cited by 16 publications

References 13 publications

Classification Of Plants And Weeds In Multi-Leaf Image With Support Vector Machine Based On Leaves Shape And Texture Features

Classification Of Plants And Weeds In Multi-Leaf Image With Support Vector Machine Based On Leaves Shape And Texture Features

A Comparative Study of White Blood cells Segmentation using Otsu Threshold and Watershed Transformation

An Efficient Implementation of Acute Lymphoblastic Leukemia Images segmentation on the FPGA

Contact Info

Product

Resources

About