Building a system to identify individuals through their speech recording can find its application in diverse areas, such as telephone shopping, voice mail and security control. However, building such systems is a tricky task because of the vast range of differences in the human voice. Thus, selecting strong features becomes very crucial for the recognition system. Therefore, a speaker recognition system based on new spin-image descriptors (SISR) is proposed in this paper. In the proposed system, circular windows (spins) are extracted from the frequency domain of the spectrogram image of the sound, and then a run length matrix is built for each spin, to work as a base for feature extraction tasks. Five different descriptors are generated from the run length matrix within each spin and the final feature vector is then used to populate a deep belief network for classification purpose. The proposed SISR system is evaluated using the English language Speech Database for Speaker Recognition (ELSDSR) database. The experimental results were achieved with 96.46 accuracy; showing that the proposed SISR system outperforms those reported in the related current research work in terms of recognition accuracy.
The basic solution to overcome difficult issues related to huge size of digital images is to recruited image compression techniques to reduce images size for efficient storage and fast transmission. In this paper, a new scheme of pixel base technique is proposed for grayscale image compression that implicitly utilize hybrid techniques of spatial modelling base technique of minimum residual along with transformed technique of Discrete Wavelet Transform (DWT) that also impels mixed between lossless and lossy techniques to ensure highly performance in terms of compression ratio and quality. The proposed technique has been applied on a set of standard test images and the results obtained are significantly encourage compared with Joint P
... Show MoreIn this paper, membrane-based computing image segmentation, both region-based and edge-based, is proposed for medical images that involve two types of neighborhood relations between pixels. These neighborhood relations—namely, 4-adjacency and 8-adjacency of a membrane computing approach—construct a family of tissue-like P systems for segmenting actual 2D medical images in a constant number of steps; the two types of adjacency were compared using different hardware platforms. The process involves the generation of membrane-based segmentation rules for 2D medical images. The rules are written in the P-Lingua format and appended to the input image for visualization. The findings show that the neighborhood relations between pixels o
... Show MoreThis research aims to know the intellectual picture the displaced people formed about aid organizations and determine whether they were positive or negative, the researchers used survey tool as standard to study the society represented by displaced people living in Baghdad camps from Shiites, Sunnis, Shabak, Turkmen, Christians, and Ezidis.
The researcher reached to important results and the most important thing he found is that displaced people living in camps included in this survey hold a positive opinion about organizations working to meet their demands but they complain about the shortfall in the health care side.
The research also found that displaced people from (Shabak, Turkmen, and Ezidi) minorities see that internati
With the continuous progress of image retrieval technology, the speed of searching for the required image from a large amount of image data has become an important issue. Convolutional neural networks (CNNs) have been used in image retrieval. However, many image retrieval systems based on CNNs have poor ability to express image features. Content-based Image Retrieval (CBIR) is a method of finding desired images from image databases. However, CBIR suffers from lower accuracy in retrieving images from large-scale image databases. In this paper, the proposed system is an improvement of the convolutional neural network for greater accuracy and a machine learning tool that can be used for automatic image retrieval. It includes two phases
... Show MoreAlthough text document images authentication is difficult due to the binary nature and clear separation between the background and foreground but it is getting higher demand for many applications. Most previous researches in this field depend on insertion watermark in the document, the drawback in these techniques lie in the fact that changing pixel values in a binary document could introduce irregularities that are very visually noticeable. In this paper, a new method is proposed for object-based text document authentication, in which I propose a different approach where a text document is signed by shifting individual words slightly left or right from their original positions to make the center of gravity for each line fall in with the m
... Show MoreRecognition is one of the basic characteristics of human brain, and also for the living creatures. It is possible to recognize images, persons, or patterns according to their characteristics. This recognition could be done using eyes or dedicated proposed methods. There are numerous applications for pattern recognition such as recognition of printed or handwritten letters, for example reading post addresses automatically and reading documents or check reading in bank.
One of the challenges which faces researchers in character recognition field is the recognition of digits, which are written by hand. This paper describes a classification method for on-line handwrit
... Show MoreSpeech recognition is a very important field that can be used in many applications such as controlling to protect area, banking, transaction over telephone network database access service, voice email, investigations, House controlling and management ... etc. Speech recognition systems can be used in two modes: to identify a particular person or to verify a person’s claimed identity. The family speaker recognition is a modern field in the speaker recognition. Many family speakers have similarity in the characteristics and hard to identify between them. Today, the scope of speech recognition is limited to speech collected from cooperative users in real world office environments and without adverse microphone or channel impairments.
Face recognition, emotion recognition represent the important bases for the human machine interaction. To recognize the person’s emotion and face, different algorithms are developed and tested. In this paper, an enhancement face and emotion recognition algorithm is implemented based on deep learning neural networks. Universal database and personal image had been used to test the proposed algorithm. Python language programming had been used to implement the proposed algorithm.