公开(公告)号：US20170024864A1

公开(公告)日：2017-01-26

申请号：US15215120

申请日：2016-07-20

Applicant: Tata Consultancy Services Limited

Inventor： Shirish Subhash KARANDE ,  Sandhya Sree THASKANI ,  Sachin P. LODHA ,  Purushotam Gopaldas RADADIA ,  Mandar Shrikant KULKARNI

IPC: G06T5/00 ,  G06T3/60 ,  G06T3/00 ,  G06T7/00

CPC classification number: G06T5/005 ,  G06T7/11 ,  G06T7/13 ,  G06T7/33 ,  G06T7/337 ,  G06T7/38 ,  G06T2207/10016 ,  G06T2207/20072 ,  G06T2207/20076 ,  G06T2207/20104

Abstract: This disclosure relates generally to image processing, and more particularly to system and method for image inpainting. In one embodiment, a method for image inpainting includes aligning a plurality of multi-view images of a scene with respect to a reference image to obtain a plurality of aligned multi-view images. A region of interest (ROI) representing a region to be removed from the reference image for image inpainting is selected. A dictionary is created by selecting image-patches from the reference image and the plurality of aligned multi-view images, and 3D rotations thereof. A priority value of each of a plurality of pixels of the ROI is created. The ROI is systematically reconstructed in the reference image based at least on the priority values of the plurality of pixels and the dictionary by computing a linear combination of two or more image-patches selected from the plurality of image-patches of the dictionary.

Abstract translation: 本公开一般涉及图像处理，更具体地涉及用于图像修复的系统和方法。 在一个实施例中，一种用于图像修复的方法包括：相对于参考图像对准场景的多个多视点图像以获得多个对准的多视图图像。 选择表示要从图像修复的参考图像中去除的区域的感兴趣区域（ROI）。 通过从参考图像和多个对准的多视图图像及其3D旋转中选择图像补丁来创建词典。 创建ROI的多个像素中的每一个的优先级值。 至少基于多个像素和字典的优先级值，通过计算从字典的多个图像块中选择的两个或更多个图像块的线性组合，在参考图像中系统地重建ROI。

公开(公告)号：US20150269528A1

公开(公告)日：2015-09-24

申请号：US14611623

申请日：2015-02-02

Applicant: Tata Consultancy Services Limited

Inventor： Mangesh Sharad GHAROTE ,  Ankita JAIN ,  Girish Keshav PALSHIKAR ,  Rajiv Radheyshyam SRIVASTAVA ,  Sachin P. LODHA

IPC: G06Q10/10

CPC classification number: G06Q10/1053 ,  G06Q10/06311 ,  G06Q50/20

Abstract: System(s) and method(s) for generating campus recruitment plan for facilitating selection of a candidate for an organization is disclosed. A ranking score is assigned to each college from a list of colleges. Number of candidates to be selected from each college is determined. A predefined number of panels from a large pool of panels by using demographic details of each employee of the organization are selected. A utility score for each panel of the predefined number of panels by using the demographic details and recruitment capability of each employee is calculated. Based on skill set of each interviewer and each candidate, a panel-candidate matching index is computed. An optimal number of interview panels from the predefined number of panels for interviewing the number of candidates are selected based on the panel-candidate matching index and the utility score to generate the campus recruitment plan by using an optimization technique.

Abstract translation: 公开了用于生成校园招聘计划以促进组织候选人的选择的系统和方法。 从大学名单中的每个学院分配一个排名得分。 确定每所大学的候选人人数。 选择通过使用组织的每个员工的人口统计信息从大型面板池中预定义数量的面板。 计算通过使用每个员工的人口统计信息和招聘能力，预定数量的面板的每个面板的效用评分。 根据每个访问者和每个候选人的技能组合，计算候选人候选人匹配指数。 根据候选人候选人匹配指标和公用事业评分，选择预定数量的面试面试人数的最佳面试面板，以通过优化技术生成校园招聘计划。