Showing papers by "Adnan Khashman published in 2006"
01 Oct 2006
TL;DR: ICIS, an intelligent coin identification system that uses a neural network and pattern averaging to recognize rotated coins at various degrees, was implemented and the results were found to be encouraging.
Abstract: The use of neural networks to simulate our perception of patterns is important in developing intelligent recognition systems. Currently, coin identification by machines relies on the assessment of the coin's physical parameters. An intelligent coin identification system that uses coin patterns for identification helps prevent confusion between different coins of similar physical dimensions. In this paper, an intelligent coin identification system (ICIS) is proposed. ICIS uses a neural network and pattern averaging to recognize rotated coins at various degrees. Slot machines in Europe accept the new Turkish 1 Lira coin as a 2 Euro coin due to physical similarities. A 2 Euro coin is roughly worth 4 times the new Turkish 1 Lira. ICIS was implemented to identify the 2-EURO and 1-TL coins and the results were found to be encouraging.
33 citations
28 May 2006
TL;DR: A novel approach to face recognition is introduced by simulating the ability to recognize “familiar” faces after a quick “glance” using pattern averaging and neural networks.
Abstract: The human ability to recognize objects has not so far been matched by intelligent machines. This is more evident when it comes to recognizing faces, where a quick human “glance” is sufficient to recognize a “familiar” face. Face recognition has recently attracted more research aimed at developing reliable recognition by machines. Current face recognition methods rely on detecting certain features within a face and using these features for face recognition. This paper introduces a novel approach to face recognition by simulating our ability to recognize “familiar” faces after a quick “glance” using pattern averaging and neural networks. A real-life application will be presented throughout recognizing the faces of 30 persons. Time costs and the neural network parameters will be described, in addition to future work aimed at further improving the developed system.
22 citations
04 Dec 2006
TL;DR: Experimental results suggest that using pattern averaging; globally or locally, performs well as part of a fast and efficient intelligent face recognition system.
Abstract: Face recognition has lately attracted more research aimed at developing intelligent machine recognition which uses information within the encoded facial patterns to learn and recognize the objects. This paper investigates the efficiency of using Global and Local pattern averaging for facial data encoding prior to training a neural network using the averaged patterns. Averaging is a simple but efficient method that creates "fuzzy" patterns as compared to multiple "crisp" patterns, which provide the neural network with meaningful learning while reducing computational expense. A real-life application will be presented throughout recognizing the faces of 60 persons using our database and the ORL face database. Experimental results suggest that using pattern averaging; globally or locally, performs well as part of a fast and efficient intelligent face recognition system.
19 citations
01 Jan 2006
TL;DR: In this paper, a rotation-invariant intelligent coin identification system (ICIS) is presented that uses a neural network and pattern averaging to recognize rotated coins at various degrees.
Abstract: When developing intelligent recognition systems, our perception of patterns can be simulated using neural networks. An intelligent coin identification system that uses coin patterns for classification helps prevent confusion between different coins of similar physical dimensions. Currently, coin identification by machines relies on the assessment of the coin’s physical parameters. In this paper, a rotation-invariant intelligent coin identification system (ICIS) is presented. ICIS uses a neural network and pattern averaging to recognize rotated coins at various degrees. Slot machines in Europe accept the new Turkish 1-Lira coin as a 2-Euro coin due to physical similarities. A 2-Euro coin is roughly worth 4 times the new Turkish 1-Lira. ICIS was implemented to identify the 2 EURO and 1 TL coins and the results were found to be encouraging.
13 citations
Proceedings Article•
27 May 2006TL;DR: A rotation-invariant intelligent coin identification system (ICIS) that uses a neural network and pattern averaging to recognize rotated coins by 15 degrees is proposed.
Abstract: Neural networks have been used in the development of intelligent systems that simulate pattern recognition and object identification. Coin identification by machines relies currently on the assessment of the physical parameters of a coin. An intelligent coin identification system that uses coin patterns for identification helps preventing confusion between different coins of similar physical dimensions. This paper proposes a rotation-invariant intelligent coin identification system (ICIS) that uses a neural network and pattern averaging to recognize rotated coins by 15 degrees. Slot machines in Europe accept the new Turkish 1 Lira coin as a 2 Euro coin due to physical similarities; however, the 2 Euro coin is roughly worth 4 times the new Turkish 1 Lira. ICIS was implemented to identify the 2 EURO and the 1 TL coins and the results were found to be encouraging.
9 citations
01 Dec 2006
TL;DR: Experimental results suggest that the developed method performs well, thus providing a fast and efficient method for text separation, and a comparison will be drawn between MDTh and five other well known and efficient thresholding methods.
Abstract: Thresholding is a simple and efficient method for image enhancement and segmentation of grayscale documents, where the relationship of pixel values in the documents can provide an effective single point for the separation of the background and foreground layers. Document analysis and effective separation of text may provide useful data for electronic storage systems and libraries. This paper presents a novel method namely, mass-difference thresholding (MDTh) for enhancement and text separation from documents. MDTh will be implemented using 30 documents that have various levels of noise and color. A comparison will be drawn between MDTh and five other well known and efficient thresholding methods. Experimental results suggest that the developed method performs well, thus providing a fast and efficient method for text separation.
5 citations
Journal Article•
TL;DR: In this article, a fast intelligent face recognition system that uses essential face features averaging and a neural network to identify multi-expression faces was presented, which was implemented on 180 images of 30 persons.
Abstract: Over the past four years there has been a marginal increase in research on developing advanced information technologies that can be efficiently used for national and international security in our war against terrorism. The list of wanted persons who are still free is getting larger, however, in most cases there is a database containing their face images and this can be used in the development of face recognition systems. A human face is an extremely complex object with features that can vary over time, sometimes very rapidly. This paper presents a fast intelligent face recognition system that uses essential face features averaging and a neural network to identify multi-expression faces. A real life application using this method is implemented on 180 images of 30 persons. Experimental results suggest that this simple but efficient system performs well, thus providing a fast intelligent system for recognizing faces with different expressions.
3 citations
23 May 2006
TL;DR: A fast intelligent face recognition system that uses essential face features averaging and a neural network to identify multi-expression faces is presented, thus providing a fast intelligent system for recognizing faces with different expressions.
Abstract: Over the past four years there has been a marginal increase in research on developing advanced information technologies that can be efficiently used for national and international security in our war against terrorism. The list of wanted persons who are still free is getting larger, however, in most cases there is a database containing their face images and this can be used in the development of face recognition systems. A human face is an extremely complex object with features that can vary over time, sometimes very rapidly. This paper presents a fast intelligent face recognition system that uses essential face features averaging and a neural network to identify multi-expression faces. A real life application using this method is implemented on 180 images of 30 persons. Experimental results suggest that this simple but efficient system performs well, thus providing a fast intelligent system for recognizing faces with different expressions.
3 citations
Journal Article•
TL;DR: A face recognition system that uses eyes, nose and mouth approximations for training a neural network to recognize faces in different expressions such as natural, smiley, sad and surprised is presented.
Abstract: A human face is a complex object with features that can vary over time. Face recognition systems have been investigated while developing biometrics technologies. This paper presents a face recognition system that uses eyes, nose and mouth approximations for training a neural network to recognize faces in different expressions such as natural, smiley, sad and surprised. The developed system is implemented using our face database and the ORL face database. A comparison will be drawn between our method and two other face recognition methods; namely PCA and LDA. Experimental results suggest that our method performs well and provides a fast, efficient system for recognizing faces with different expressions.
2 citations
27 Sep 2006
TL;DR: In this article, a face recognition system that uses eyes, nose and mouth approximations for training a neural network to recognize faces in different expressions such as natural, smiley, sad and surprised is presented.
Abstract: A human face is a complex object with features that can vary over time. Face recognition systems have been investigated while developing biometrics technologies. This paper presents a face recognition system that uses eyes, nose and mouth approximations for training a neural network to recognize faces in different expressions such as natural, smiley, sad and surprised. The developed system is implemented using our face database and the ORL face database. A comparison will be drawn between our method and two other face recognition methods; namely PCA and LDA. Experimental results suggest that our method performs well and provides a fast, efficient system for recognizing faces with different expressions.
1 citations