The feature extraction step plays major role for proper object classification and recognition, this step depends mainly on correct object detection in the given scene, the object detection algorithms may result with some noises that affect the final object shape, a novel approach is introduced in this paper for filling the holes in that object for better object detection and for correct feature extraction, this method is based on the hole definition which is the black pixel surrounded by a connected boundary region, and hence trying to find a connected contour region that surrounds the background pixel using roadmap racing algorithm, the method shows a good results in 2D space objects.
Keywords: object filling, object detection, objec

      This work addressed the assignment problem (AP) based on fuzzy costs, where the objective, in this study, is to minimize the cost. A triangular, or trapezoidal, fuzzy numbers were assigned for each fuzzy cost. In addition, the assignment models were applied on linguistic variables which were initially converted to quantitative fuzzy data by using the Yager’sorankingi method. The paper results have showed that the quantitative date have a considerable effect when considered in fuzzy-mathematic models.

Image Fusion Using A Convolutional Neural Network

Recognizing speech emotions is an important subject in pattern recognition. This work is about studying the effect of extracting the minimum possible number of features on the speech emotion recognition (SER) system. In this paper, three experiments performed to reach the best way that gives good accuracy. The first one extracting only three features: zero crossing rate (ZCR), mean, and standard deviation (SD) from emotional speech samples, the second one extracting only the first 12 Mel frequency cepstral coefficient (MFCC) features, and the last experiment applying feature fusion between the mentioned features. In all experiments, the features are classified using five types of classification techniques, which are the Random Forest (RF),

An approach is depended in the recent years to distinguish any author or writer from other by analyzing his writings or essays. This is done by analyzing the syllables of writings of an author. The syllable is composed of two letters; therefore the words of the writing are fragmented to syllables and extract the most frequency syllables to become trait of that author. The research work depend on analyzed the frequency syllables in two cases, the first, when there is a space between the words, the second, when these spaces are ignored. The results is obtained from a program which scan the syllables in the text file, the performance is best in the first case since the sequence of the selected syllables is higher than the same syllables in

Scientific development has occupied a prominent place in the field of diagnosis, far from traditional procedures. Scientific progress and the development of cities have imposed diseases that have spread due to this development, perhaps the most prominent of which is diabetes for accurate diagnosis without examining blood samples and using image analysis by comparing two images of the affected person for no less than a period. Less than ten years ago they used artificial intelligence programs to analyze and prove the validity of this study by collecting samples of infected people and healthy people using one of the Python program libraries, which is (Open-CV) specialized in measuring changes to the human face, through which we can infer the

Face Identification is an important research topic in the field of computer vision and pattern recognition and has become a very active research area in recent decades. Recently multiwavelet-based neural networks (multiwavenets) have been used for function approximation and recognition, but to our best knowledge it has not been used for face Identification. This paper presents a novel approach for the Identification of human faces using Back-Propagation Adaptive Multiwavenet. The proposed multiwavenet has a structure similar to a multilayer perceptron (MLP) neural network with three layers, but the activation function of hidden layer is replaced with multiscaling functions. In experiments performed on the ORL face database it achieved a

The aim of this work is to study reverse osmosis characteristics for copper sulfate hexahydrate (CuSO4.6H2O), nickel sulfate hexahydrate (NiSO4.6H2O) and zinc sulfate hexahydrate (ZnSO4.6H2O) removal from aqueous solution which discharge from some Iraqi factories such as Alnasser Company for mechanical industries. The mode of operation of reverse osmosis was permeate is removed and the concentrate of metals solution is recycled back to the feed vessel. Spiral-wound membrane is thin film composite membrane (TFC) was used to conduct this study on reverse osmosis. The variables studied are metals concentrations (50 – 150 ppm) and time (15 – 90 min). It was found that increasing the time results in an increase in concentration of metal in p

In this research, we did this qualitative and quantitative study in order to improve the assay of aspirin colorimetrically using visible spectrophotometer. This method depends on aqueous hydrolysis of aspirin and then treating it with the ferric chloride acidic solution to give violet colored complex with salicylic acid, as a result of aspirin hydrolysis, which has a maximum absorption at 530nm. This procedure was applied to determine the purity of aspirin powder and tablet. The results were approximately comparative so that the linearity was observed in the high value of both correlation coefficient (R= 0.998) and Determination Coefficient or Linearity (R2= 0.996) while the molar absorpitivity was 1.3× 103 mole