Search

A deep convolutional neural network model is presented here which uses deep learning features for text and non-text region segmentation from document images. The key objective is to extract text regions from the complex layout document images without any prior knowledge of segmentation. In a real-world scenario, a document or magazine images contain various text information along with non-text regions such as symbols, logos, pictures, and graphics. Extraction of text regions from non-text regions is challenging. To mitigate these issues, an efficient and robust segmentation technique has been proposed in this paper. The implementation of the proposed model is divided into three phases: (a) a method for pre-processing of document images using different patch sizes is employed to handle the situations for variants of text fonts and sizes in mage; (b) a deep convolutional neural network model is proposed to predict the text or non-text or ambiguous region within the image; (c) a method for post-processing of document image is proposed to handle the situation where the image has complex ambiguous regions by utilizing the recursive partitioning of those regions into their proper classes (i.e. text or non-text) and then the system accumulates the responses of those predictive patches with varying resolutions for handling the situation of text fonts variations within the image. Extensive computer simulations have been conducted using a collection of complex layout magazine images from Google sites and the ICDAR 2015 database. Results are collected and compared with state-of-the-art methods. It reveals that the proposed model is robust and more effective as compared to state-of-the-art methods.

Essential genes are considered to be the necessary genes that are required to sustain life of different organisms. These genes encode proteins which maintain central metabolism, DNA replications, translation of Genes, basic cellular structure and mediate transport process within and out of the cell. The identification of essential genes is one of the essential problems in computational genomics. In this present study, in order to discriminate essential genes from the other genes from the non-biologist’s perspective, the purine and pyrimidine (Pu-Py) distribution over the essential genes of four exemplary species namely: Homo Sapiens (HS), Arabidopsis Thaliana (AT), Drosophila Melanogaster (DM) and DanioRerio (DR) are thoroughly experimented using some quantitative methods. Moreover, the Indigent classification method has also been deployed for classification on the essential genes of the said species. Based on Shannon entropy (SE), Fractal dimension (FD), Hurst exponent (HE), purine and pyrimidine (Pu-Py) bases distribution the ten different clusters have been generated for the essential genes of the four species. Some proximity results are also reported herewith the clusters of the essential genes.

Biological regulatory network can be modeled through a set of Boolean functions. These set of functions enable graph representation of the network structure and hence the dynamics of the network can be seen easily. In this article, the regulations of such network have been explored in term of interaction graph. With the help of Boolean function decomposition this work presents an approach for construction of interaction graphs. This decomposition technique is also used to reduce the network state space of the cell cycle network Fission Yeast for finding the singleton attractors. Some special classes of Boolean functions with respect to the interaction graphs have been discussed. A unique recursive procedure is devised that uses the Cartesian product of sets starting from the set of one variable Boolean function. Interaction graphs generated with these Boolean functions have only positive/negative edges and the corresponding state spaces have periodic attractors with length one/two.