Wyniki wyszukiwania - BazTech

1

A retinal image authentication framework based on a graph-based representation algorithm in a two-stage matching structure

Khakzar M., Pourghassem H.

Biocybernetics and Biomedical Engineering

|

2017

|

Vol. 37, no. 4

742--759

EN

Retinal vascular pattern has many valuable characteristics such as uniqueness, stability and permanence as a basis for human authentication in security applications. This paper presents an automatic rotation-invariant retinal authentication framework based on a novel graph-based retinal representation scheme. In the proposed framework, to replace the retinal image with a relational mathematical graph (RMG), we propose a novel RMG definition algorithm from the corresponding blood vessel pattern of the retinal image. Then, the unique features of RMG are extracted to supplement the authentication process in our framework. The authentication process is carried out in a two-stage matching structure. In the first stage of this scenario, the defined RMG of enquiry image is authenticated with enrolled RMGs in the database based on isomorphism theory. If the defined RMG of enquiry image is not isomorphic with none enrolled RMG in the database, in the second stage of our matching structure, the authentication is performed based on the extracted features from the defined RMG by a similarity-based matching scheme. The proposed graph-based authentication framework is evaluated on VARIA database and accuracy rate of 97.14% with false accept ratio of zero and false reject ratio of 2.85% are obtained. The experimental results show that the proposed authentication framework provides the rotation invariant, multi resolution and optimized features with low computational complexity for the retina-based authentication application.

2

Automatic brain hemorrhage segmentation and classification algorithm based on weighted grayscale histogram feature in a hierarchical classification structure

Shahangian B., Pourghassem H.

Biocybernetics and Biomedical Engineering

|

2016

|

Vol. 36, no. 1

217--232

EN

Brain hemorrhage is the first cause of death in ages between 15 and 24, and the third after heart diseases and cancers in other ages. Saving the lives of such patients completely depends on detecting the correct location and type of the hemorrhage in an early stage. In this paper, an automatic brain hemorrhage detection and classification algorithm on CT images is proposed. To achieve this purpose, after preprocessing, a modified version of Distance Regularized Level Set Evolution (MDRLSE) is used to detect and separate the hemorrhage regions. Then a perfect set of shape and texture features from each detected hemorrhage region are extracted. Moreover, we define a synthetic feature that is called weighted grayscale histogram feature. In this feature, valuable information from shape, position and area of the hemorrhage are integrated with the grayscale histogram of hemorrhage region. After that a synthetic feature selection algorithm is applied to select the most convenient features. Eventually, the seg- mented regions are classified into four types of the hemorrhages such as EDH, ICH, SDH and IVH by a hierarchical structure of classification. Our proposed algorithm is evaluated on a perfect set of CT-scan images and obtains the accuracy rate of 96.15%, 95.96% and 94.87% for the segmentation of the EDH, ICH, and SDH types, respectively. Also our proposed classification structure provides the accuracy rate of 92.46% and 94.13% for the first and second classifiers of the hierarchical classification structure for classifying the IVH from normal class and the EDH, ICH and SDH hemorrhage classes, respectively.

3

An automatic aneurysm extraction algorithm in fused brain digital subtraction angiography images

Momeni S., Pourghassem H.

Biocybernetics and Biomedical Engineering

|

2015

|

Vol. 35, no. 4

264--275

EN

Brain aneurysm is one of the most life-threatening events, which is associated with a high rate of mortality and disability. There are many factors, which specify the best treatment option for each particular patient. In this paper, an automatic computer-aided extraction algorithm for brain aneurysm, from fused digital subtraction angiography (DSA) images is proposed. In this algorithm, firstly, to remove vessel structure, morphological operations based on multi-directional structure elements and nonlinear diffusion filtering are used. Then, by applying circular Hough transform and region growing algorithms, the aneurysm extraction procedure is performed. In this step, to overcome to poor edge gradient of aneurysm, we define a labeled diffused image which specifies the region growing conditions. Finally, by using morphological operators, the aneurysm extraction performance of our algorithm is improved. In addition, the radius of extracted aneurysm is defined and reported as a geometric feature. The experimental results indicate that our proposed algorithm obtains accuracy rate of 77.5% for the aneurysm extraction on 30 abnormal cases.