A Feature Extraction Method Based on Morphological Operators for Automatic Classification of Leukocytes

Gómez-Gil, Pilar; Ramírez-Cortés, Manuel; Gonzalez, Jesús A.; Pedrero, A.G.; Prieto-Castro, C.I.; Valencia, David; Lobato, Ruben; Alonso, Jose E.

doi:10.1109/micai.2008.41

Cited by 14 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The morphological operation is a well-known technique used in image processing and computer vision for manipulating image features based on their shapes [22]. However, some methods need a considerable amount of computational or intensive memory to implement, and improve the speed and accuracy [1].…”

Section: B Facial Feature Localizationmentioning

confidence: 99%

Detection of facial expressions based on Morphological face features and Minimum Distance Classifier

Bozed

Adjei

Mansour

2013

14th International Conference on Sciences and Techniques of Automatic Control &Amp; Computer Engineering - STA'2013

View full text Add to dashboard Cite

A facial expression is one of the non-verbal information that plays an important role in understanding faceto-face communications. Therefore, facial expressions are the most important means of detecting emotions and behavioral analysis science. Although human being have ability recognize the face practically without any effort, but facial recognition system is still challenging by machine. This paper addresses the problem of detecting facial expressions of the human face through the analysis of images and subsequent application to video sequences. This work concentrates on the design of a facial expression detection system used to recognize facial emotions by focusing on the analysis of still images based on Morphological features and Minimum Distance Classifier (MDC) for classification.

show abstract

Section: B Facial Feature Localizationmentioning

confidence: 99%

Detection of facial expressions based on Morphological face features and Minimum Distance Classifier

Bozed

Adjei

Mansour

2013

14th International Conference on Sciences and Techniques of Automatic Control &Amp; Computer Engineering - STA'2013

View full text Add to dashboard Cite

show abstract

“…In this paper, the morphological pattern spectrum is used as a tool to create different feature vectors. This technique has been used in different works for feature extraction [17,18,19,20], because it gives us information about the shape and size of the objects in the image, with very good properties of translation and rotation invariance. In [17], it is presented a novel feature-extraction method based on the morphological pattern spectrum for a biometric shape-based hand recognition system and this is tested using a Euclidean distance classifier.…”

Section: Introductionmentioning

confidence: 99%

“…In [17], it is presented a novel feature-extraction method based on the morphological pattern spectrum for a biometric shape-based hand recognition system and this is tested using a Euclidean distance classifier. In [18], it is presented an automatic leukocyte classification based on mathematical morphology to create a feature vector which was tested using 4 different classifiers, obtaining the best results with ANN. These examples indicate the relevance of the morphological pattern spectrum for feature extraction and also the relevance of the ANN in pattern recognition problems arising in the vast field of medical applications.…”

Section: Introductionmentioning

confidence: 99%

Automatic classification of thermal patterns in diabetic foot based on morphological pattern spectrum

Hernandez-Contreras

Peregrina-Barreto

Rangel-Magdaleno

et al. 2015

Infrared Physics & Technology

View full text Add to dashboard Cite

“…In this paper, the boundary of WBCs in the images is manually determined to decrease the effects of segmentation errors, but the nucleus and cytoplasm of leukocytes are separated automatically by a fuzzy C-means clustering method. Also, several researchers have previously proposed features to differentiate leukocytes [15][16][17][18][19][20]. Although many useful researches have been done for classification of WBCs, many of them have some defects.…”

Section: Introductionmentioning

confidence: 99%

Selection of the best features for leukocytes classification in blood smear microscopic images

et al. 2014

View full text Add to dashboard Cite

Automatic differential counting of leukocytes provides invaluable information to pathologist for diagnosis and treatment of many diseases. The main objective of this paper is to detect leukocytes from a blood smear microscopic image and classify them into their types: Neutrophil, Eosinophil, Basophil, Lymphocyte and Monocyte using features that pathologists consider to differentiate leukocytes. Features contain color, geometric and texture features. Colors of nucleus and cytoplasm vary among the leukocytes. Lymphocytes have single, large, round or oval and Monocytes have singular convoluted shape nucleus. Nucleus of Eosinophils is divided into 2 segments and nucleus of Neutrophils into 2 to 5 segments. Lymphocytes often have no granules, Monocytes have tiny granules, Neutrophils have fine granules and Eosinophils have large granules in cytoplasm. Six color features is extracted from both nucleus and cytoplasm, 6 geometric features only from nucleus and 6 statistical features and 7 moment invariants features only from cytoplasm of leukocytes. These features are fed to support vector machine (SVM) classifiers with one to one architecture. The results obtained by applying the proposed method on blood smear microscopic image of 10 patients including 149 white blood cells (WBCs) indicate that correct rate for all classifiers are above 93% which is in a higher level in comparison with previous literatures.

show abstract

A Feature Extraction Method Based on Morphological Operators for Automatic Classification of Leukocytes

Cited by 14 publications

References 10 publications

Detection of facial expressions based on Morphological face features and Minimum Distance Classifier

Detection of facial expressions based on Morphological face features and Minimum Distance Classifier

Automatic classification of thermal patterns in diabetic foot based on morphological pattern spectrum

Selection of the best features for leukocytes classification in blood smear microscopic images

Contact Info

Product

Resources

About