In the last decade, several Convolutional Networks have been developed for the semantic segmentation, which have shown excellent performance in recognizing and labeling objects in images. Most of these Networks involve large-scale architectures that can detect tens or hundreds of predefined classes. With the exception of Fully Convolutional Networks, most applications use architectures that, after Convolutional layers, use a common classifier to classify the extracted features. In this paper, the method of converting a Network, which as classifier, has two flatten and dense layers (Fully connected), to a Fully Convolutional Network is described. The main advantage of this method is the ability to work on inputs of variable size and produce an output map instead of a number, which is the advantage of Fully Convolutional Networks. Newer models of the Deep Learning area generally use training images in which areas of interest are determined by masks, but in the proposed method only labeled images are given to the Network. The details of the proposed method are expressed in the form of a new problem of classification of boards with calligraphy of Shekasteh-Nastaliq and Suls, and classification of apple leaf diseases (as two-class problems) and the problem of identifying hand written Persian digits. For this purpose, first a Convolutional Network with the last Fully connected layer is designed and trained for square images. Then a new Fully Convolutional model is defined based on the previous model and the weights of the previous model are fed to the new model. The only difference between the two models is in the last layer, but the new model will be able to work on input images of any size. Experimental results show the efficiency of the proposed approach.

The development of automatic road and building detection systems in aerial imagery are always faced with challenges such as the appearance of buildings, illumination changes, imaging angles, and the density of roads and buildings in urban areas, to name a few. In recent years, employing multi-layered approach in artificial neural Networks, known as deep neural Networks, has attracted many researchers in this field (and the other fields alike), achieving stunning results. However, the use of Fully connected layers in this approach, significantly increases the average processing time and results in an overfitted model. In addition, in most of these methods, a single-class approach has been considered. That is, detecting the roads and the buildings from natural scenes is not possible at the same time, and therefore, it is necessary to build separate binary models for each of them. The main goal of this research is to design a new architecture by which the produced model can be able to simultaneously detect roads and buildings from natural scenes, and thus minimizing the complexity of the classification process. In addition, in the proposed architecture, excluding all Fully connected layers from the traditional multi-layered architectures is considered in order to reduce the average processing time. The results of the experiments performed on the Massachusetts dataset, show that the proposed architecture performs 38% faster than the other deep neural Network-based methods, and also increases the accuracy by an average of 2%.

Optical Coherence Tomography (OCT) images are used to reveal retinal diseases and abnormalities, such as Diabetic Macular Edema (DME) and Age-related Macular Degeneration (AMD). Fluid regions are the main sign of AMD and DME and automatic fluid segmentation models are very helpful for diagnosis, treatment, and follow-up. This paper presents a two-path Neutrosophic (NS) Fully Convolutional Networks, referred as TPNFCN, as a Fully-automated model for fluid segmentation. For this task, OCT images are first transferred to NS domain and then Inner Limiting Membrane (ILM) and Retinal Pigmentation Epithelium (RPE) layers as first and last layers of retina are segmented by graph shortest path algorithms in NS domain, respectively. Afterwards, a basic block of FCN is presented for fluid segmentation and this block is used in the architecture of the proposed TPNFCN. Both the basic block and TPNFCN are evaluated on 600 OCT scans of 24 AMD subjects containing different fluid types. Results reveal that the proposed basic block and TPNFCN outperform five competitive models by improvement of 6.28%, 4.44% and 2.54% with respect to sensitivity, dice coefficients, and precision, respectively. It is also demonstrated that the proposed TPNFCN is robust against low number of training samples in comparison with current models.