A bag of features based approach for classification of motile sperm cells

Daniel Paredes Soto; Maria Luisa Davila Garcia; Lyudmila Mihaylova

doi:10.1109/iThings-GreenCom-CPSCom-SmartData.2017.21

A bag of features based approach for classification of motile sperm cells

Daniel Paredes Soto, Maria Luisa Davila Garcia, Lyudmila Mihaylova

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

Abstract

The analysis of sperm morphology remains an essential process for diagnosis and treatment of male infertility. In this paper, a novel framework based on image processing is proposed to classify sperm cell images affected by noise due to their movement. This represents a challenge, articularly because the cells are not fixed or stained. The proposed framework is based on Speeded-Up Robust Features (SURF) combined with Bag of Features (BoF) models to quantise features computed by SURF. Support Vector Machines (SVMs) are used to classify the simplified feature vectors, extracted from sperm cell images, into normal, abnormal and noncell categories. The performance of this framework is compared to a similar model where the Histogram of Oriented Gradients (HOG) is used to extract features and SVMs is applied for their classification. The proposed framework allows to achieve classification results with an average accuracy of 90% with the SURF approach compared to 78% with the HOG approach.

Original language	English
Title of host publication	10th IEEE International Conference on Cyber, Physical and Social Computing
Publisher	The Institute of Electrical and Electronics Engineers (IEEE)
Pages	104-109
DOIs	https://doi.org/10.1109/iThings-GreenCom-CPSCom-SmartData.2017.21
Publication status	Published - 2017
Externally published	Yes

Access to Document

10.1109/iThings-GreenCom-CPSCom-SmartData.2017.21

Cite this

@inproceedings{3163f933671a4ac19a963fd05e5960da,

title = "A bag of features based approach for classification of motile sperm cells",

abstract = "The analysis of sperm morphology remains an essential process for diagnosis and treatment of male infertility. In this paper, a novel framework based on image processing is proposed to classify sperm cell images affected by noise due to their movement. This represents a challenge, articularly because the cells are not fixed or stained. The proposed framework is based on Speeded-Up Robust Features (SURF) combined with Bag of Features (BoF) models to quantise features computed by SURF. Support Vector Machines (SVMs) are used to classify the simplified feature vectors, extracted from sperm cell images, into normal, abnormal and noncell categories. The performance of this framework is compared to a similar model where the Histogram of Oriented Gradients (HOG) is used to extract features and SVMs is applied for their classification. The proposed framework allows to achieve classification results with an average accuracy of 90% with the SURF approach compared to 78% with the HOG approach.",

author = "{Paredes Soto}, Daniel and {Davila Garcia}, {Maria Luisa} and Lyudmila Mihaylova",

year = "2017",

doi = "10.1109/iThings-GreenCom-CPSCom-SmartData.2017.21",

language = "English",

pages = "104--109",

booktitle = "10th IEEE International Conference on Cyber, Physical and Social Computing",

publisher = "The Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

A bag of features based approach for classification of motile sperm cells. / Paredes Soto, Daniel; Davila Garcia, Maria Luisa; Mihaylova, Lyudmila.

10th IEEE International Conference on Cyber, Physical and Social Computing. The Institute of Electrical and Electronics Engineers (IEEE), 2017. p. 104-109.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A bag of features based approach for classification of motile sperm cells

AU - Paredes Soto, Daniel

AU - Davila Garcia, Maria Luisa

AU - Mihaylova, Lyudmila

PY - 2017

Y1 - 2017

N2 - The analysis of sperm morphology remains an essential process for diagnosis and treatment of male infertility. In this paper, a novel framework based on image processing is proposed to classify sperm cell images affected by noise due to their movement. This represents a challenge, articularly because the cells are not fixed or stained. The proposed framework is based on Speeded-Up Robust Features (SURF) combined with Bag of Features (BoF) models to quantise features computed by SURF. Support Vector Machines (SVMs) are used to classify the simplified feature vectors, extracted from sperm cell images, into normal, abnormal and noncell categories. The performance of this framework is compared to a similar model where the Histogram of Oriented Gradients (HOG) is used to extract features and SVMs is applied for their classification. The proposed framework allows to achieve classification results with an average accuracy of 90% with the SURF approach compared to 78% with the HOG approach.

AB - The analysis of sperm morphology remains an essential process for diagnosis and treatment of male infertility. In this paper, a novel framework based on image processing is proposed to classify sperm cell images affected by noise due to their movement. This represents a challenge, articularly because the cells are not fixed or stained. The proposed framework is based on Speeded-Up Robust Features (SURF) combined with Bag of Features (BoF) models to quantise features computed by SURF. Support Vector Machines (SVMs) are used to classify the simplified feature vectors, extracted from sperm cell images, into normal, abnormal and noncell categories. The performance of this framework is compared to a similar model where the Histogram of Oriented Gradients (HOG) is used to extract features and SVMs is applied for their classification. The proposed framework allows to achieve classification results with an average accuracy of 90% with the SURF approach compared to 78% with the HOG approach.

U2 - 10.1109/iThings-GreenCom-CPSCom-SmartData.2017.21

DO - 10.1109/iThings-GreenCom-CPSCom-SmartData.2017.21

M3 - Conference contribution

SP - 104

EP - 109

BT - 10th IEEE International Conference on Cyber, Physical and Social Computing

PB - The Institute of Electrical and Electronics Engineers (IEEE)

ER -