In this project, we develop an algorithm that takes in an image and identifies if contains a dog or a human. If it does contain either a dog or a human, the algorithm will classify the dog's breed or the dog breed that closely resembles that human. This problem falls under the popular category of computer vision. To solve these problems we will be using machine learning methods. We will look at a couple of different methods for each problem and identify which is better. We will also focus on the dog breed classifier and use off-the-shelf tools for the human and dog detectors.

Perched in his fire tower high above the pine trees, Nick Dutton leans back and nods to the cascading hills and mountains behind him. "I love being out here, just away from stuff," he says. "I mean, you can't really complain." Dutton, a fire tower operator, is sitting in his office, a tiny cabin propped high above the treetops by metal supports that sway with the wind. His walls are littered with compass points and references, each a guide to the bush stretching in every direction along the eastern ACT-NSW border.

As most recently proposed methods for human detection have achieved a sufficiently high recall rate within a reasonable number of proposals, in this paper, we mainly focus on how to improve the precision rate of human detectors. In order to address the two main challenges in precision improvement, i.e., i) hard background instances and ii) redundant partial proposals, we propose the novel PoseHD framework, a top-down pose-based approach on the basis of an arbitrary state-of-theart human detector. In our proposed PoseHD framework, we first make use of human pose estimation (in a batch manner) and present pose heatmap classification (by a convolutional neural network) to eliminate hard negatives by extracting the more detailed structural information; then, we utilize posebased proposal clustering and reranking modules, filtering redundant partial proposals by comprehensively considering (a) Positive instances (b) Hard negative instances both holistic and part information. The experimental results on multiple pedestrian benchmark datasets validate that our proposed PoseHD framework can generally improve the overall performance of recent state-of-the-art human detectors (by 2-4% in both mAP and MR metrics). Moreover, our PoseHD framework can be easily extended to object detection with large-scale object part annotations. Finally, in this paper, we present extensive ablative analysis to compare our approach with these traditional bottom-up pose-based models and highlight (c) Redundant partial proposals (in blue box) the importance of our framework design decisions.

An artificially intelligent robot that can understand sarcasm in social media posts better than humans has been developed by scientists. The algorithm can decipher the tone of tweets, and researchers say it could be used to tackle online abuse. By interpreting emoji used alongside a post's text, the robot can understand emotional subtext and identify if sarcasm is being used. A robot that can understand sarcasm in social media posts better than humans has been developed by scientists. By interpreting emoji used alongside a post's text, the AI can understand emotional subtext and identify if sarcasm is being used (stock image) Researchers created the AI, known as DeepMoji, by feeding it 1.2 billion tweets. The robot analysed each tweet to understand how 64 popular emoji were used in them to express meaning.