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.
Abstract— The growing use of digital technologies across various sectors and daily activities has made handwriting recognition a popular research topic. Despite the continued relevance of handwriting, people still require the conversion of handwritten copies into digital versions that can be stored and shared digitally. Handwriting recognition involves the computer's strength to identify and understand legible handwriting input data from various sources, including document, photo-graphs and others. Handwriting recognition pose a complexity challenge due to the diversity in handwriting styles among different individuals especially in real time applications. In this paper, an automatic system was designed to handwriting recognition
... Show MoreLighting is a very important element of treatment if the color contains many imaging system (digital cameras) and the unit of light and the light within these units are not strong , but usefel when the light is low , in different lighting intensities conditions image quality will not persist good enough and image may become dark or slightly exposed to light which leads to lower the details in image where we can not modify contrast or light ness to compensate thr decrease without losing the light and dark deatials . So we went in this research to study the variation colored texts written on the painting and lighting cases of non –regular ( a few) and different distances . As the diversity of these texts written on the board a
... Show MoreThis article investigates Iraq wars presentation in literature and media. The first section investigates the case of the returnees from the war and their experience, their trauma and final presentation of that experience. The article also investigates how trauma and fear is depicted to create an optimized image and state of fear that could in turn show Iraqi society as a traumatized society. Critics such as Suzie Grogan believes that the concept of trauma could expand to influence societies rather than one individual after exposure to trauma of being involved in wars and different major conflicts. This is reflected in Iraq as a country that was subjected to six comprehensive conflicts in its recent history, i.e. less than half a century; th
... Show MoreThe sensitive and important data are increased in the last decades rapidly, since the tremendous updating of networking infrastructure and communications. to secure this data becomes necessary with increasing volume of it, to satisfy securing for data, using different cipher techniques and methods to ensure goals of security that are integrity, confidentiality, and availability. This paper presented a proposed hybrid text cryptography method to encrypt a sensitive data by using different encryption algorithms such as: Caesar, Vigenère, Affine, and multiplicative. Using this hybrid text cryptography method aims to make the encryption process more secure and effective. The hybrid text cryptography method depends on circular queue. Using circ
... Show MoreThe tagged research problem (the outputs of the written text in conceptual art) dealt with a comparative analytical study in the concept of conceptual art trends (land art - body art - art - language).
The study consisted of four chapters. The first chapter dealt with the theoretical framework, which was represented in presenting (the research problem), which raised the following question: What is the role of the written text in the transformations of the conceptual arts?
The first chapter included (the importance of research) and (research objectives) seeking to conduct comparative research in the written text within the trends of conceptual art as a moving phenomenon in art, and to reveal the variable written text in the
... Show MoreAbstract
The perpetuity of the Quranic discourse required being suitable for all ages.
Accordingly, the method of the Glorious Quran a pre request for the conscious
investigation and realization in order to detect the core of the texts, as the Quranic
discourse is considered a general address for the humanity as a whole. For this
reason, the progress of the concerned studies neceiated that it should cope with the
current development in the age requirements and its cultural changes within ages.
The texts of the Glorious Quran lightened the human reason as being the
Creator’s miracle for it is characterized by certain merits that makes it different from
poetry and prose. It is a unique texture in its rheto
... Show MoreComputer-aided diagnosis (CAD) has proved to be an effective and accurate method for diagnostic prediction over the years. This article focuses on the development of an automated CAD system with the intent to perform diagnosis as accurately as possible. Deep learning methods have been able to produce impressive results on medical image datasets. This study employs deep learning methods in conjunction with meta-heuristic algorithms and supervised machine-learning algorithms to perform an accurate diagnosis. Pre-trained convolutional neural networks (CNNs) or auto-encoder are used for feature extraction, whereas feature selection is performed using an ant colony optimization (ACO) algorithm. Ant colony optimization helps to search for the bes
... Show More