Volkan Atalay

Projection based method for segmentation of human face and its evaluation

We detect facial features and then circumscribe each facial feature with the smallest rectangle possible by using vertical and horizontal gray value projections of pixels. The result is evaluated with respect to the manually located enclosing rectangle on the images of a publicly available database.

Silhouette-based 3-D model reconstruction from multiple images

The goal of this study is to investigate the reconstruction of three-dimensional (3-D) graphical models of real objects in a controlled imaging environment and present the work done in our group based on silhouette-based reconstruction. Although many parts of the whole system have been well-known in the literature and in practice, the main contribution of the paper is that it describes a complete, end-to-end system explained in detail. Based on a multi-image calibration method, an algorithm to extract the rotation axis of a turn-table has been developed. Furthermore, this can be extended to estimate robustly the initial bounding volume of the object to be modeled. The disadvantages of the silhouette-based reconstruction can be removed by an algorithm using photoconsistency. This algorithm has a simpler visibility check, and it eliminates the selection of threshold existing in similar algorithms. Besides, in order to construct the appearance, we use the concept of particles. The reconstruction results are shown both on real world and synthetic objects.

The random neural network model for texture generation

The generation of artifical textures is a useful function in image synthesis systems. The purpose of this paper is to describe the use of the random neural network (RN) model developed by Gelenbe to generate various textures having different characteristics. An eight parameter model, based on a choice of the local interaction parameters between neighbouring neurons in the plane, is proposed. Numerical iterations of the field equations of the neural network model, starting with a randomly generated gray-level image, are shown to produce textures having different desirable features such as granularity, inclination, and randomness. The experimental evaluation shows that the random network provides good results, at a computational cost less than that of other approaches such as Markov random fields. Various examples of textures generated by our method are presented.

An automated differential blood count system

While the early diagnosis of hematopoietic system disorders is very important in hematology, it is a highly complex and time consuming task. The early diagnosis requires a lot of patients to be followed-up by experts which, in general is unfeasible because of the required number of experts. The differential blood counter (DBC) system that we have developed is an attempt to automate the task performed manually by experts in routine. In our system, the cells are segmented using active contour models (snakes and balloons), which are initialized using morphological operators. Shape based and texture based features are utilized for the classification task. Different classifiers such as k-nearest neighbors, learning vector quantization, multi-layer perceptron and support vector machine are employed.

Feature extraction and classification of blood cells for an automated differential blood count system

The differential blood counter system we developed is an attempt to automate the task performed manually by experts in routine. Feature extraction and classification are two important components of our automated system. In this paper, classification of blood cells using various approaches including neural network based classifiers and support vector machine are presented together with the features used in the classification.

PCA for gender estimation: which eigenvectors contribute?

A pruning schema is applied to multi-layer perceptron (MLP) gender classifier MLP uses eigenvector coefficients of the face space created by principal component analysis (PCA). We show that pruning improves the initial MLP performance by preserving the most effective input while eliminating most of the units and connections. Pruning is also used as a tool to monitor which eigenvectors contribute to gender estimation. In addition, by usage of FERET face database, we test the PCA approach on gender estimation task in a bigger setting than the previous experiments.

A hierarchical representation of form documents for identification and retrieval

Abstract. In this paper, we present a logical representation for form documents to be used for identification and retrieval. A hierarchical structure is proposed to represent the structure of a form by using lines and the XY-tree approach. The approach is top-down and no domain knowledge such as the preprinted data or filled-in data is used. Geometrical modifications and slight variations are handled by this representation. Logically identical forms are associated to the same or similar hierarchical structure. Identification and the retrieval of similar forms are performed by computing the edit distances between the generated trees.

Repulsive attractive network for baseline extraction on document images

Abstract This paper describes a new framework, called repulsive attractive (RA) network for baseline extraction on document images. The RA network is an energy minimizing dynamical system, which interacts with the document text image through the attractive and repulsive forces defined over the network components and the document image. Experimental results indicate that the network can successfully extract the baselines under heavy noise and overlaps between the ascending and descending portions of the characters of adjacent lines. The proposed framework is applicable to a wide range of image processing applications, such as curve fitting, segmentation and thinning.

Computer vision based mouse

We describe a computer vision based mouse, which can control and command the cursor of a computer or a computerized system using a camera. In order to move the cursor on the computer screen the user simply moves the mouse shaped passive device placed on a surface within the viewing area of the camera. The video generated by the camera is analyzed using computer vision techniques and the computer moves the cursor according to mouse movements. The computer vision based mouse has regions corresponding to buttons for clicking. To click a button the user simply covers one of these regions with his/her finger.

Vision-based single-stroke character recognition for wearable computing

Particularly when compared to traditional tools such as a keyboard or mouse, wearable computing data entry tools offer increased mobility and flexibility. Such tools include touch screens, hand gesture and facial expression recognition, speech recognition, and key systems. We describe a new approach for recognizing characters drawn by hand gestures or by a pointer on a users forearm captured by a digital camera. We draw each character as a single, isolated stroke using a Graffiti-like alphabet. Our algorithm enables effective and quick character recognition. The resulting character recognition system has potential for application in mobile communication and computing devices such as phones, laptop computers, handheld computers and personal data assistants.