-
公开(公告)号：US10402979B2
公开(公告)日：2019-09-03
申请号：US15593497
申请日：2017-05-12
发明人： Mani Abedini , Rajib Chakravorty , Rahil Garnavi , Munawar Hayat
IPC分类号： G06T7/10 , G06T7/13 , G06K9/46 , G06K9/52 , G06K9/62 , G06T7/00 , G06K9/68 , G06T7/143 , G06T7/90 , G06T7/11
摘要： A robust segmentation technique based on multi-layer classification technique to identify the lesion boundary is described. The inventors have discovered a technique based on training several classifiers such that to classify each pixel as lesion versus normal Each classifier is trained on a specific range of image resolutions. Then, for a new test image, the trained classifiers are applied on the image. Then by fusing the prediction results in pixel level a probability map is generated. In the next step, a thresholding method is applied to convert the probability map to a binary mask, which determines a mole border.
-
2.发明申请公开(公告)号：US20190156449A1
公开(公告)日：2019-05-23
申请号：US15819730
申请日：2017-11-21
发明人： Mani Abedini , Rajib Chakravorty , Rahil Garnavi , Zongyuan Ge
摘要： A computer-implemented screening method, system, and computer program product including detecting at least two disassembled components of an object spread across multiple sensor scan images of at least one container, storing a record of each disassembled component correlated with contextual information of each owner of each container corresponding to a sensor scan image, and flagging the owner of the container in the sensor scan image based on a joint assessment of the sensor scan image including a disassembled component that can be combined with another disassembled component in a different sensor scan image to assemble the object and the contextual information of each owner.
-
公开(公告)号：US10229513B2
公开(公告)日：2019-03-12
申请号：US15400295
申请日：2017-01-06
发明人： Rajib Chakravorty , Lenin Mehedy
摘要： A method for modifying digital media comprises receiving one or more digital media items, determining a plurality of colors and one or more associations between the colors in the one or more digital media items; collecting a color vision profile from one or more color blind individuals in an environment; analyzing the color vision profiles to determine common colors visible by the one or more color-blind individuals; identifying a color scheme for modifying the one or more digital media items to correspond to the common colors visible by the one or more color-blind individuals; and modifying the one or more digital media items using the color scheme.
-
公开(公告)号：US20180122065A1
公开(公告)日：2018-05-03
申请号：US15336293
申请日：2016-10-27
CPC分类号： G06T7/0012 , G06K9/4642 , G06K9/6212 , G06K2209/05 , G06T7/73 , G06T2207/20081 , G06T2207/30096
摘要： A method for image analysis comprises receiving one or more images of a plurality of lesions captured from a body of a person, extracting one or more features of the plurality of lesions from the one or more images, analyzing the extracted one or more features, wherein the analyzing comprises determining a distance between at least two lesions with respect to the extracted one or more features, and determining whether any of the plurality of lesions is an outlier based on the analyzing.
-
公开(公告)号：US20180116498A1
公开(公告)日：2018-05-03
申请号：US15854984
申请日：2017-12-27
CPC分类号： A61B3/0025 , A61B3/102 , A61B3/1225 , A61B5/7275 , G06K9/0061 , G06K9/00617 , G06K9/6215 , G06K2209/05
摘要： An AMD prediction model utilizes an OCT image estimation model. The OCT image estimation module is created by segmenting an OCT image to generate an OCT projection image for each of multiple biological layers; extracting from each of the generated OCT projection images a first set of features; extracting a second set of features from an input retinal fundus image; for each respective biological layer, registering the input retinal fundus image to the respective OCT projection image by matching at least some of the second set of features with corresponding ones of the first set of features; repeating the above with changes to the input retinal fundus image; and modelling how the changes to the input retinal fundus image are manifest at the correspondingly registered projection images. Estimated OCT projection images can then be generated for the multiple biological layers from a given retinal fundus image.
-
公开(公告)号：US11455469B2
公开(公告)日：2022-09-27
申请号：US16686667
申请日：2019-11-18
发明人： Nebula Alam , Rajib Chakravorty , Lida Ghahremanlou , Jorge Andres Moros Ortiz , Dheerender Velu Palani
IPC分类号： G06F17/00 , G06F40/30 , G06F3/04817 , G06Q10/10 , G06Q10/00
摘要： A sentiment analyzer obtains natural language media input and determines sentiment of the natural language media input. A personality analyzer obtains data indicative of a personality of an originator of the natural language media input and determines a personality metric of the originator of the natural language media input. The sentiment of the natural language media input and the personality metric of the originator of the natural language media input are combined to obtain a personality-based sentiment of the natural language media input. The natural language media input is provided to a receiver together with a representation of the personality-based sentiment of the natural language media input.
-
公开(公告)号：US11151781B2
公开(公告)日：2021-10-19
申请号：US16185782
申请日：2018-11-09
发明人： Lenin Mehedy , Rajib Chakravorty
摘要： A technique relates to an imaging apparatus. Extensions are coupled to a support structure, the extensions being spaced a predefined distance from one another, the extensions having a length that protrudes from the support structure. Light sources are coupled to the extensions such that the light sources are positioned to irradiate a scalp. Sensors are coupled to the extensions, the sensors being positioned at an angle to capture images of the scalp having been irradiated by the light sources.
-
公开(公告)号：US20200151948A1
公开(公告)日：2020-05-14
申请号：US16185782
申请日：2018-11-09
发明人： Lenin Mehedy , Rajib Chakravorty
摘要： A technique relates to an imaging apparatus. Extensions are coupled to a support structure, the extensions being spaced a predefined distance from one another, the extensions having a length that protrudes from the support structure. Light sources are coupled to the extensions such that the light sources are positioned to irradiate a scalp. Sensors are coupled to the extensions, the sensors being positioned at an angle to capture images of the scalp having been irradiated by the light sources.
-
公开(公告)号：US20200029109A1
公开(公告)日：2020-01-23
申请号：US16042456
申请日：2018-07-23
发明人： Ermyas Abebe , Rajib Chakravorty , Lenin Mehedy
IPC分类号： H04N21/2343 , H04N21/25 , H04N21/258 , H04N21/8405
摘要： A system, method and program product for system for processing audio visual (AV) content items during playback. A system is disclosed that includes: a controller for selecting a content item and filtering the content item during playback based on filtering parameters; an audience identification system that identifies members of an audience intended to view the content item and obtains user attributes of each member of the audience; and a filtering manager that calculates the filtering parameters based on the user attributes and metadata tags associated with the content item, wherein the metadata tags are obtained from a remote metadata repository that generates metadata tags from feedback obtained from participating system users.
-
公开(公告)号：US20200000331A1
公开(公告)日：2020-01-02
申请号：US16564524
申请日：2019-09-09
发明人： Rajib Chakravorty , Rahil Garnavi , Pallab Roy
摘要： A computer-implemented method includes obtaining an image of a retinal fundus. A plurality of features is extracted from the image of the retinal fundus. The plurality of features includes at least one feature based on anatomical domain knowledge of the retinal fundus and at least one response of a pre-trained deep convolutional neural network to at least a portion of the image of the retinal fundus. The retinal fundus is determined to belong to a left eye or a right eye, based on an analysis of the plurality of features.
-
-
-
-
-
-
-
-
-
搜索结果
46 条记录 (耗时 0.018 秒)
