Search

The process of detect the text from the natural image is complex and difficult process because the variance by the devises that take the images and different the texts that found in images in the orientation, size and style. Given the importance the texts in images in the several of application of computer vision. In this paper dependent on the spatial natural images and on the spatial data set for the street sign that include the texts by the different size and different orientation. In this paper detected the texts in images by using robust method by using several algorithms, at the first stage making preprocessing for the image to blur the image and reduce the nose on it by Gaussian blur, second stage making processing that include canny edge detection to detect the edges and dilation, third stage applying connected component to filling all objects in image then applying stroke width transform(SWT) to detect the letter candidate and applying the system on the several images that include different types of texts.

In this paper, the fire color feature is analysis and test on a set of color spaces (RGB, HSV, YCbCr, Lab, Yiq) to account the hue component and determination the best color space to represent the properties of fire and used in fire detection to increase accuracy and reduce the detection time and false alarms,four common types of fire (wood, cork, cloth, paper or cardboard ) were used to compare them with an image containing all the basic colors and analyze them and calculating Scale factor that depending on the histogram for hues value

In the last few years, and due to the vast widespread of social media applications, texts have become more important and get more attention. Since texts, in general, are carrying a lot of information that can be extracted and analyzed. Several researchers have done significant works in text classification. Within different scripts such as English and other western languages, several challenges and obstacles have been addressed with such a field of research. Regarding the Arabic language, the process is different from other vital languages since Arabic is considered an orthographic language that depends on the word shape. It is not easy to apply the standard text preprocessing techniques since it affects the word meaning. This paper evaluates Arabic short text classification using three standard Naïve Bayes classifiers. In our method, we classify the thesis and dissertations using their titles to perform the classification process. The collected dataset is collected from different repositories by using standard scrapping techniques. Our method classifies the document based on their titles to be placed in the desired specialization. Several preprocessing techniques have been applied, such as (punctuation removal, stop words removal, and space vectorization). For feature extraction, we adopt the TF-IDF method. We implemented three types of Naïve Bayes classifiers which are (Multinomial Naïve Bayes, Complemented Naïve Bayes, and Gaussian Naïve Bayes). The study results showed that Complemented Naïve Bayes Classifier proposed the best performance with (0.84) of accuracy for the testing phase. The results of the study are promising to be applied with different short text classifications.

Deep learning of multi-layer computational models allowed processing to recognize data representation at multiple levels of abstraction. These techniques have greatly improved the latest ear recognition technology. PNN is a type of radiative basis for classification problems and is based on the Bayes decision-making base, which reduces the expected error of classification. In this paper, strong features of images are used to give a good result, therefore, SIFT method using these features after adding improvements and developments. This method was one of the powerful algorithms in matching that needed to find energy pixels. This method gives stronger feature on features and gives a large number of a strong pixel, which is considered a center and neglected the remainder of it in our work. Each pixel of which is constant for image translation, scaling, rotation, and embedded lighting changes in lighting or 3D projection. Therefore, the interpretation is developed by using a hierarchical cluster method; to assign a set of properties (find the approximation between pixels) were classified into one.

Characterizing of visual objects is an important role in pattern recognition that can be performed through shape analysis. Several approaches have been introduced to extract relevant information of a shape. The complexity of the shape is the most widely used approach for this purpose where fractal dimension and generalized fractal dimension are methodologies used to estimate the complexity of the shapes. The box counting dimension is one of the methods that used to estimate fractal dimension. It is estimated basically to describe the self-similarity in objects. A lot of objects have the self-similarity; fingerprint is one of those objects where the generalized box counting dimension is used for recognizing of the fingerprints to be utilized for authentication process. A new fractal dimension method is proposed in this paper. It is verified by the experiment on a set of natural texture images to show its efficiency and accuracy, and a satisfactory result is found. It also offers promising performance when it is applied for fingerprint recognition.

The segmentation performance is topic to suitable initialization and best configuration of supervisory parameters. In medical image segmentation, the segmentation is very important when the diagnosing becomes very hard in medical images which are not properly illuminated. This paper proposes segmentation of brain tumour image of MRI images based on spatial fuzzy clustering and level set algorithm. After performance evaluation of the proposed algorithm was carried on brain tumour images, the results showed confirm its effectiveness for medical image segmentation, where the brain tumour is detected properly.

Blood cells are composed of erythrocytes (Red Blood Cells (RBCs)), the shape of RBC changes when the body suffers from different diseases such as Anemia. Classification of such diseases helps the medical technician to decide the type of Anemia in Laboratory analyzes in the hospitals. This paper proposed an automatic classification algorithm, which discriminates the different types of Anemia using Principal Component Analysis (PCA) algorithm and Decision tree. The proposed algorithm consists of four steps, at the first step preprocessing steps are applied on the RBC image, these RBC images then segmented in the second step, features are extracted using moment invariant in third step, this features are considered input to PCA so as to produced features vectors, at a final step features vector are inputted to Decision Tree to classify RBC image. Best classifications rates are (92%) obtained when using PCA algorithm compared with (74.1 %) which are obtained without applying PCA algorithm.