The essence of an image is a projection from a 3-D scene onto a 2-D plane, during which the depth information is lost. The 3-D point corresponding to a specific image point is constrained to be on the line of sight. From a single image, it is very difficult to determine the depth information of various object points in an image. If two or more 2-D images are used, then the relative depth point of the image points can be calculated which can be further used to reconstruct the 3-D image by projecting the image points which includes the depth information as well. This paper presents two techniques namely binocular disparity and photometric stereo for depth calculation and 3-D reconstruction of an object in an image as it requires minimum user intervention.Binocular disparity method requires a pair of stereo images to compute disparity and depth to generate the desired 3-D view whereas the photometric stereo method requires multiple images under different light directions.
Recycling of engineering design is increasing exponentially in order to reduce the conceptual designing phase time due to rapid increase in technology. This leads to increase in frequent retrieval of the 3D models through web searching mechanism. So, it becomes a necessary challenge to design a 3D search engine which can search 3D models accurately as well as efficiently. The 3D searching is a technique developed to help the web users for extracting 3D models like complex engineering parts, various purpose graphical models, etc. The search engine takes input in the form of queries like text, 2D sketches, 3D sketches, 3Dmodel, 2Dmodel etc. When input queries is matched with the existing model in the database or similar model that are present in the database, the best multiple result is provided to user. This paper describes the basics of query by sketch which takes input by sketching manually with the aid of user interface. This input is normalized and further processed by Voxelization, Skeltonization and create Skeletal graph which is then mapped to database to extract best possible match. However, the main focus of this paper is to discuss the process of Voxelization method in very simple steps, as it plays a very important aspect in 3D searching.
Topographic Map (TM) highlights essential morphological features. Some notable features include contours, elevation values, etc. It may be either distinct or overlapped with other features. All these attributes are annotations written using distinct color codes. These features along with their associated attributes is used for various morphological analyses. The process of extracting morphological features along with attributes from map is referred as digitization. Digitization is done manually or with an abled automatic computational process. The manual process is tedious and time-consuming whereas automated process takes comparatively lesser time but generates quality results. With advanced learning techniques, quality and integrity of result have considerably increased. CNN adopts traditional MLP where convolution layers replaces intermediate hidden layers in the network. Convolutional layers build a versatile mechanism to enable the detector to identify the features. This paper presents comparison of RCNN and Faster RCNN model result to detect and locate text present in the TM.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.