The task of conversion of grayscale images into colorful ones is a complex problem because the same intensity of light can correspond to different colors in three channel color models. This usually requires manual modifications to attain artifact-free quality. This paper looks into this problem and aims at the conversion of grayscale image to colorful ones. In the proposed approaches, support vector regression (SVR) is trained upon the features using SLIC and fuzzy c-means algorithm. Scores of trials and tests demonstrate that our algorithm gives an excellent performance in terms of quality, speed, and several feature learning benchmarks.

Cultures across the world have evolved to have unique patterns despite shared ingredients and cooking techniques. Using data obtained from RecipeDB, an online resource for recipes, we extract patterns in 26 world cuisines and further probe for their inter-relatedness. By application of frequent itemset mining and ingredient authenticity we characterize the quintessential patterns in the cuisines and build a hierarchical tree of the world cuisines. This tree provides interesting insights into the evolution of cuisines and their geographical as well as historical relatedness.

Cultures across the world are distinguished by the idiosyncratic patterns in their cuisines. These cuisines are characterized in terms of their substructures such as ingredients, cooking processes and utensils. A complex fusion of these substructures intrinsic to a region defines the identity of a cuisine. Accurate classification of cuisines based on their culinary features is an outstanding problem and has hitherto been attempted to solve by accounting for ingredients of a recipe as features. Previous studies have attempted cuisine classification by using unstructured recipes without accounting for details of cooking techniques. In reality, the cooking processes/techniques and their order are highly significant for the recipe's structure and hence for its classification. In this article, we have implemented a range of classification techniques by accounting for this information on the RecipeDB dataset containing sequential data on recipes. The state-of-the-art RoBERTa model presented the highest accuracy of 73.30% among a range of classification models from Logistic Regression and Naive Bayes to LSTMs and Transformers.

For a person with only one arm, it is not very easy to grasp objects from their surroundings. Human beings have evolved to use both hands to carry out even ordinary tasks. Hence, specially-abled people with only one hand suffer difficulties in their day to day life. We present the development of HandAid, equipment designed to assist single-handed people. HandAid is a semi-autonomous device consisting of a redundant robotic manipulator attachment that can be attached to the shoulder and serves as a prosthetic arm to aid the user. The arm solely cannot identify the object to interact with; hence it is assisted by a headgear containing a stereo-camera and a laser pointer. The user can move his head and guide the laser to the concerned object, the located object is extracted using segmentation, and the point cloud of the object is created to obtain the collision-free path which is traced by the arm to grasp the object. This novel concurrent approach is implemented on ROS, integrated with OpenCV and moveit! for precise recognition and efficient manipulation of the object. Besides, the bot has been simulated on the gazebo to validate the results.

Oil and gas organizations across the globe rely heavily on underwater pipelines and water transportation systems. Due to exposure of pipe and ship surfaces to hostile environments like turbulence, water currents, and underwater vegetation, it is not uncommon to observe cracks on exposed material. Thus, regular inspection and maintenance are imperative. Such tasks need to be extremely precise which render the task to be time-consuming and the hostility of the environment renders the task to be dangerous and expensive. This calls for a robotic solution to the problem. In this paper, we propose a 7 DOF autonomous underwater welding arm along with autonomous crack detection, localization, and welding of the crack. We propose a real-time crack identification and segmentation technique using computer vision algorithms to facilitate real-time path generation for the arm, trajectory following, and motion planning. This methodology has been tested by mounting the designed arm on an AUV in the UnderWater Simulator and moving it using the MoveIt! package. The paper also implements a closed-loop control mechanism with an adaptive motion planner using pose tracking to overcome external disturbances during welding operations. The results indicate that the path tracking problem can be solved using computer vision algorithms in the absence of dynamic models.

Present-day organizations continue to expose their critical information infrastructures over the Internet for facilitating accessibility; substantially raising concerns about the security of data from both outsiders and insiders. In this paper, we propose a novel approach for detecting intrusive attacks on databases by assessing the risk for incoming transaction based upon the conflation of multiple behavior-based components for the user. In a database intrusion detection system for a role-based access (RBAC) environment, it is not sufficient to focus on role-based features as every user within the same role has a degree of uniqueness. Moreover, traditional database intrusion detection systems classify the incoming transactions into two classes (Malicious or Non-malicious), taking the same action for all transactions that are labeled as malicious irrespective of the damage it can cause to the system. Our approach, Role and User Behavior-based Risk Assessment (RUBRA) uses both role-behavior and user-behavior based features for detecting an intrusive attack. Further, we also quantify the risk associated with the incoming transaction, streamlining the countermeasure process. Experiments on stochastic datasets show promising results on both detection and labeling of malicious transactions.

Abstract Cooking is the act of turning nature into the culture, which has enabled the advent of the omnivorous human diet. The cultural wisdom of processing raw ingredients into delicious dishes is embodied in their cuisines. Recipes thus are the cultural capsules that encode elaborate cooking protocols for evoking sensory satiation as well as providing nourishment. As we stand on the verge of an epidemic of diet-linked disorders, it is eminently important to investigate the culinary correlates of recipes to probe their association with sensory responses as well as consequences for nutrition and health. RecipeDB (https://cosylab.iiitd.edu.in/recipedb) is a structured compilation of recipes, ingredients and nutrition profiles interlinked with flavor profiles and health associations. The repertoire comprises of meticulous integration of 118 171 recipes from cuisines across the globe (6 continents, 26 geocultural regions and 74 countries), cooked using 268 processes (heat, cook, boil, simmer, bake, etc.), by blending over 20 262 diverse ingredients, which are further linked to their flavor molecules (FlavorDB), nutritional profiles (US Department of Agriculture) and empirical records of disease associations obtained from MEDLINE (DietRx). This resource is aimed at facilitating scientific explorations of the culinary space (recipe, ingredient, cooking processes/techniques, dietary styles, etc.) linked to taste (flavor profile) and health (nutrition and disease associations) attributes seeking for divergent applications. Database URL: https://cosylab.iiitd.edu.in/recipedb