Content-based image retrieval (CBIR) in large medical image archives is a challenging and necessary task. Generally, different feature extraction methods are used to assign expressive and invariant features to each image such that the search for similar images comes down to feature classification and/or matching. The present work introduces a new image retrieval method for medical applications that employs a convolutional neural network (CNN) with recently introduced Radon barcodes. We combine neural codes for global classification with Radon barcodes for the final retrieval. We also examine image search based on regions of interest (ROI) matching after image retrieval. The IRMA dataset with more than 14,000 x-rays images is used to evaluate the performance of our method. Experimental results show that our approach is superior to many published works.

The ability of a service or personal robot to learn new tasks from human teaching is important if it is to be multi-functioning and serve users a lifetime. Considering the vast variation of tasks, work environments, and nature of potential teachers or users who may not have knowledge in robotics, the problem of task teaching and learning can be difficult to achieve. Current methods of robot teaching and learning do not yet enable the robot to learn different types of tasks from the teaching by a general user. This paper presents a human-inspired method of robot task learning from human instructive hand-to-hand teaching. The method is novel in including an introduction of the complete task to the robot before task demonstration, a voting algorithm for segmenting the demonstrated task trajectory, and a Bayesian approach to assign partitioned trajectory segments to subtasks. Also, the proposed trajectory blending scheme can generate actual task paths in real-time to adapt learned tasks to new task setups.

Although reinforcement learning (RL) emerged more than a decade ago, it is still under extensive investigation in application to large problems, where the states and actions are multi-dimensional and continuous and result in the so- called curse of dimensionality. Conventional RL methods are still not efficient enough in huge state-action spaces, while value-function generalization-based approaches require a very large number of good training examples. This paper presents an active exploratory approach to address the challenge of RL in large problems. The core principle of this approach is that the agent does not rush to the next state. Instead, it attempts a number of actions at the current state first, and then selects the action that returns the greatest immediate reward. The state resulting from performing the action is considered as the next state. Four active exploration algorithms for good actions are proposed: random-based search, opposition-based random search, search by cyclical adjustment, and opposition-based cyclical adjustment of each action dimension. The efficiency of these algorithms is determined by a visual-servoing experiment with a 6-axis robot.