Patents by Inventor Rameswar Panda

Rameswar Panda has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 10915798
    Abstract: Disclosed herein are embodiments of systems, methods, and products for a webly supervised training of a convolutional neural network (CNN) to predict emotion in images. A computer may query one or more image repositories using search keywords generated based on the tertiary emotion classes of Parrott's emotion wheel. The computer may filter images received in response to the query to generate a weakly labeled training dataset labels associated with the images that are noisy or wrong may be cleaned prior to training of the CNN. The computer may iteratively train the CNN leveraging the hierarchy of emotion classes by increasing the complexity of the labels (tags) for each iteration. Such curriculum guided training may generate a trained CNN that is more accurate than the conventionally trained neural networks.
    Type: Grant
    Filed: May 15, 2018
    Date of Patent: February 9, 2021
    Assignee: Adobe Inc.
    Inventors: Jianming Zhang, Rameswar Panda, Haoxiang Li, Joon-Young Lee, Xin Lu
  • Patent number: 10672115
    Abstract: Systems and methods are disclosed for processing an image to detect anomalous pixels. An image classification is received from a trained convolutional neural network (CNN) for an input image with a positive classification being defined to represent detection of an anomaly in the image and a negative classification being defined to represent absence of an anomaly. A backward propagation analysis of the input image for each layer of the CNN generates an attention mapping that includes a positive attention map and a negative attention map. A positive mask is generated based on intensity thresholds of the positive attention map and a negative mask is generated based on intensity thresholds of the negative attention map. An image of segmented anomalous pixels is generated based on an aggregation of the positive mask and the negative mask.
    Type: Grant
    Filed: December 6, 2017
    Date of Patent: June 2, 2020
    Assignee: Siemens Corporation
    Inventors: Rameswar Panda, Ziyan Wu, Arun Innanje, Ramesh Nair, Ti-chiun Chang, Jan Ernst
  • Publication number: 20190287234
    Abstract: Systems and methods are disclosed for processing an image to detect anomalous pixels. An image classification is received from a trained convolutional neural network (CNN) for an input image with a positive classification being defined to represent detection of an anomaly in the image and a negative classification being defined to represent absence of an anomaly. A backward propagation analysis of the input image for each layer of the CNN generates an attention mapping that includes a positive attention map and a negative attention map. A positive mask is generated based on intensity thresholds of the positive attention map and a negative mask is generated based on intensity thresholds of the negative attention map. An image of segmented anomalous pixels is generated based on an aggregation of the positive mask and the negative mask.
    Type: Application
    Filed: December 6, 2017
    Publication date: September 19, 2019
    Inventors: Rameswar Panda, Ziyan Wu, Arun Innanje, Ramesh Nair, Ti-chiun Chang, Jan Ernst
  • Patent number: 10215714
    Abstract: Method and system for detecting defects on surface of object are presented. An imaging device captures images of surface of object under ambient and dark field illumination conditions. The images are processed with a plurality of image operations to detect area of potential defect at location on surface of object based on predictable pattern consisting of bright and shadow regions. Kernels are defined corresponding to configurations of dark field illumination sources to enhance detecting potential defect. Areas of potential defect are cut from processed images to sub images. Sub images are stitched together to generate hypothesis of potential defect at location on surface of object. The hypothesis is classified with a classifier to determine whether the potential defect is true defect. The classifier is trained with training data having characteristics of true defect. The method provides efficient automated detection of micro defects on surface of object.
    Type: Grant
    Filed: August 16, 2017
    Date of Patent: February 26, 2019
    Assignee: SIEMENS ENERGY, INC.
    Inventors: Ziyan Wu, Rameswar Panda, Jan Ernst, Kevin P. Bailey
  • Publication number: 20190056333
    Abstract: Method and system for detecting defects on surface of object are presented. An imaging device captures images of surface of object under ambient and dark field illumination conditions. The images are processed with a plurality of image operations to detect area of potential defect at location on surface of object based on predictable pattern consisting of bright and shadow regions. Kernels are defined corresponding to configurations of dark field illumination sources to enhance detecting potential defect. Areas of potential defect are cut from processed images to sub images. Sub images are stitched together to generate hypothesis of potential defect at location on surface of object. The hypothesis is classified with a classifier to determine whether the potential defect is true defect. The classifier is trained with training data having characteristics of true defect. The method provides efficient automated detection of micro defects on surface of object.
    Type: Application
    Filed: August 16, 2017
    Publication date: February 21, 2019
    Inventors: Ziyan Wu, Rameswar Panda, Jan Ernst, Kevin P. Bailey
  • Publication number: 20190057498
    Abstract: Method and system for detecting line defects on surface of object are presented. An imaging device captures images of surface of object under ambient and dark field illumination conditions. The images are processed with a plurality of image operations to detect areas of potential defects based on predictable pattern consisting of bright and shadow regions. Areas of potential defect are cut from processed images to sub images. Sub images are stitched together to generate hypotheses of potential defects at locations on surface of object. The hypotheses are classified to determine whether the potential defects are true defects at the locations. Line defect is detected by refining line segments detected on the processed image based on criteria. The criteria include distance from the true defects to the line segments and slops between the true defects and the line segments are less than threshold values.
    Type: Application
    Filed: August 16, 2017
    Publication date: February 21, 2019
    Inventors: Rameswar Panda, Ziyan Wu, Jan Ernst, Kevin P. Bailey
  • Patent number: 10192301
    Abstract: Method and system for detecting line defects on surface of object are presented. An imaging device captures images of surface of object under ambient and dark field illumination conditions. The images are processed with a plurality of image operations to detect areas of potential defects based on predictable pattern consisting of bright and shadow regions. Areas of potential defect are cut from processed images to sub images. Sub images are stitched together to generate hypotheses of potential defects at locations on surface of object. The hypotheses are classified to determine whether the potential defects are true defects at the locations. Line defect is detected by refining line segments detected on the processed image based on criteria. The criteria include distance from the true defects to the line segments and slops between the true defects and the line segments are less than threshold values.
    Type: Grant
    Filed: August 16, 2017
    Date of Patent: January 29, 2019
    Assignee: SIEMENS ENERGY, INC.
    Inventors: Rameswar Panda, Ziyan Wu, Jan Ernst, Kevin P. Bailey