Geo-Landmark Recognition and Detection

The widespread use of smartphones and mobile data in the present-day society has exponentially led to the interaction with the physical world. The increase in the amount of image data in web and mobile applications makes image search slow and inaccurate. Landmark recognition, an image retrieval task, faces its challenges due to the uncommon structure it possesses, such as, buildings, cathedrals, castles or museums. These are shot from various angles which are often different from each other, for instance, the exterior and interior of a landmark. This paper makes use of a Convolutional Neural Networks (CNN) based efficient recognition system that serves in navigation, to organize photo collections, identify fake reports and unlabeled landmarks from historical data. It identifies landmarks correctly from a variety of images taken at different viewpoints as well as distances. An appropriate CNN architecture helps to provide the best solution for the currently selected dataset.

Landmark Recognition Using Ensemble-Based Machine Learning Models

Recognizing landmarks in images with machine learning is an excellent topic for research today. Landmark recognition is an important field in computer vision. In this field, we train the machine learning models to identify and recognize the closed distinctly distinguishable objects in a digital image. In general, if we consider a digital image to be a set of coordinates of different pixels, a landmark is said to be enclosed in that closed polygon formed by the pixels that may be considered as a distinct and distinguishable thing in one or the other sense. Landmark recognition is an important subject area of image classification since it is considered as one of the first steps towards reaching complete computer vision. The extremely broad definition of a landmark makes it eligible to be considered as one of the leading problems in image classification tasks. Since the task is considered to be a very broad one, the solutions to the task hold no easy procedures. This chapter explores landmark recognition using ensemble-based machine learning models.

A Hybrid Approach for Landmark Recognition using Deep Local Features and Residual Network-50

As smartphones and mobile data become universal in modern society, the opportunities to interact with the real world would grow tremendously. Latest Technologies such as Oculus Rift and Google Glass attempt to bridge the gap between the virtual and the material. With advancements in computing speed and image recognition, the idea of augmented reality (AR) becomes more tangible. However, the sheer complexity of image processing and feature recognition is an area of concern for AR. A successful AR system must distinguish among many landmarks and identify or classify the existence of new landmarks. AR algorithms naturally lend themselves to using deep learning because of the adaptability required to various factors. This paper aims to develop and refine a deep learning algorithm that can distinguish landmarks from images using a google landmark database of known landmarks. Instance-level recognition is universally used in areas of Landmark recognition and is also the upcoming research area. Instance-level recognition is the brain behind Landmark recognition. As in Landmarks, the goal is to seek an instance of a common group instead of a group, requiring new deep learning techniques. In this paper, three different VGG16, Inceptionv3, and ResNet50 models are trained using the transfer learning technique and a Pure Convolutional Neural Network (CNN) model is also trained from scratch. This paper proposes a modified version of the ResNet50 model to increase the accuracy and performance of the models used. The revised version of Resnet50 contains an additional Deep Local Features (DeLF) processing layer before generating the final output.

Development of intra-oral automated landmark recognition (ALR) for dental and occlusal outcome measurements

SummaryPrevious studies embracing digital technology and automated methods of scoring dental arch relationships have shown that such technology is valid and accurate. To date, however there is no published literature on artificial intelligence and machine learning to completely automate the process of dental landmark recognition.This study aimed to develop and evaluate a fully automated system and software tool for the identification of landmarks on human teeth using geometric computing, image segmenting and machine learning technology.239 digital models were used in the automated landmark recognition (ALR) validation phase, 161 of which were digital models from cleft palate subjects aged 5 years. These were manually annotated to facilitate qualitative validation. Additionally, landmarks were placed on 20 adult digital models manually by three independent observers. The same models were subjected to scoring using the ALR software and the differences (in mm) were calculated. All the teeth from the 239 models were evaluated for correct recognition by the ALR with a breakdown to find which stages of the process caused the errors.The results revealed that 1526 out of 1915 teeth (79.7%) were correctly identified, and the accuracy validation gave 95% confidence intervals for the geometric mean error of [0.285, 0.317] for the humans and [0.269, 0.325] for ALR – a negligible difference.It is anticipated that ALR software tool will have applications throughout Dentistry and anthropology and in research will constitute an objective tool for handling large datasets without the need for time intensive employment of experts to place landmarks manually.

Using formal ontology for the representation of morphological properties of anatomical structures in endoscopic surgery

In this paper we present results to the problem of an adequate and compact symbolic representation of morphological features of anatomical structures that serve as surgical landmarks for automated assistance in endoscopic surgery using the General Formal Ontology (GFO) as a formal framework. For this purpose, we employed a translation from this first-order logic representation to a more compact description logic based formalism with the associated benefits, such as the availability of decidable reasoning procedures, for the purpose of automated landmark recognition in a hybrid symbolic/subsymbolic AI approach.