Abstract: The present disclosure discloses methods and systems for detecting tampering of an infrared (IR) security mark in a document. The method includes receiving the document including the IR security mark, wherein the IR security mark further includes one or more security texts and/or images. The document is scanned to generate scanned data. A portion of the scanned data including the IR security mark is segmented into a plurality of blocks such as blocks of size 32*32. Thereafter, a ratio of white to black pixels is calculated for each block. The calculated ratio is compared with a known threshold for each block. Upon comparison, the IR security mark is detected as a tampered security mark.

Abstract: The present disclosure discloses methods and systems for detecting an IR security mark in a document based on known color information and halftone frequency information. The method includes receiving a document from a user, including an IR security mark. Then, location information, color information and halftone frequency information are received from the user. The document is scanned. Based on the color information and the location information, the IR security mark is extracted from the scanned document. After this, halftone frequency information of the extracted IR security mark is verified. Based on the verification, text in the extracted IR security mark is identified and is then compared with one or more pre-stored IR security marks to ascertain whether the IR security mark in the document is an authentic security mark.

Abstract: The invention relates to method and system for feature extraction from an input image from a plurality of images in an image sensor pipeline. The method includes determining a number of logical convolutional operations to be performed, within a reconfigurable convolutional cluster engine, based on a size of an input feature map corresponding to the input image; performing a set of concurrent row wise convolutions on the input feature map, based on the number of logical convolutional operations; performing at least one of a maximum pooling or an average pooling operation on the set of corresponding convolution output through one or more pooling elements to generate a set of pooling output; and generating an output feature map based on the set of pooling output.

Abstract: Disclosed is a reconfigurable parallel 3-Dimensional (3-D) convolution engine for performing 3-D Convolution and parallel feature map extraction on an image. The reconfigurable parallel 3-D convolution engine further comprises a plurality of CNN reconfigurable engines configured to perform 3-D convolution, in parallel, to process a plurality of feature maps, a kernel memory space, present in each instance of CNN reconfigurable engine, capable for holding a set of parameters associated to a network layer having each operational instance of CNN reconfigurable engine, and at least one memory controller, an Input Feature Map Memory (FMM) cluster and an Output FMM cluster.

Abstract: The present disclosure discloses methods and systems for adjusting text colors in scanned documents. The method includes receiving a document for scanning from a user. Then, the document is scanned to generate scanned data. The scanned data is segmented into an image layer and one or more text layers, wherein the one or more text layers include textual content. Thereafter, the text color of the textual content in each text layer is identified. Then, the identified text color of the textual content in the text layer is compared with one or more pre-defined colors. Based on comparison, the text color of the textual content in each text layer is adjusted to match with the one or more pre-defined colors thereby generates a modified text layer. Finally, the modified text layer and the image layer are combined to create a final scanned document.

Abstract: Disclosed is a convolution operator system comprising a Convolution Neural Network (CNN) reconfigurable engine including a plurality of Mini Parallel Rolling Engines (MPREs) for performing a convolution operation concurrently on an image. An input router receives image data. A controller allocates image data to computing blocks through a set of data flow control blocks. Each computing block produces a convolution output corresponding to each row of the image. The controller allocates a plurality of group having one or more computing blocks to generate a set of convolution output. Further, a pipeline adder aggregates the set of convolution output to produce an aggregated convolution output. An output router transmits either the convolution output or the aggregated convolution output for performing subsequent convolution operation to generate a convolution result for the image data.

Abstract: The present disclosure discloses methods and systems for automatically determining one or more optimal scan settings to manage an output size of a document submitted for scanning at a multi-function device. The method includes receiving the document for scanning from a user, wherein the document includes one or more pages having content. As scanning activity is progressed at the multi-function device, an output file size is displayed to the user via a user interface in real-time. Then, an input from the user is received on the displayed output file size. Based on the input from the user, one or more scan settings are determined to be applied on the already scanned pages and remaining pages of the document to be scanned, to manage the output size of an output scanned file to be generated. Thereafter, the determined one or more scan settings are applied such that the output size of the scanned file is in accordance with the requirement. Finally, the scanned file is output of the required size.

Abstract: The present disclosure discloses methods and systems for adding one or more annotations from a printed version of a document to a digital version of the document. The methods and systems include receiving the printed document with one or more annotations, which represent review comments of a reviewer. The printed document including one or more annotations is scanned to obtain a scanned document. Thereafter, the scanned document is compared with the original digital version of the document to identify the one or more annotations. The identified one or more annotations are then extracted and added to the digital version of the document to obtain a new digital version, which can be used for changes by the user or any other user.

Abstract: The present disclosure discloses methods and systems for allowing a user to add one or more bookmarks while scanning a document. The method includes receiving a document for scanning from a user. Once received, a user interface is displayed to the user to select an option to add one or more bookmark to the document. The document is scanned to get scanned pages of the document. Based on the selection of the option by the user, one or more bookmarks are added to one or more scanned pages of the document. The scanned document including the one or more bookmarked pages is sent to the one or more recipients for the desired action.

Abstract: A computer-implemented method and system for processing a document page is based on text and non-text detections in an image path. An object block is generated for each image content identified within an input page. the blocks are extracted from the input document for downstream processing. Then, the object blocks are classified based on whether the content is text or non-text. The extracted non-text objects—which are specified by their bounding boxes—are processed separately from the rest of the content. The processing is performed on the text content blocks in parallel. However, when error diffusion is employed, the error diffusion is performed sequentially on the non-text content blocks to avoid stitching artifacts between individually error diffused patches in non-text areas.

Abstract: The disclosure discloses methods and systems for handling drifting of colors in printing. The method includes receiving a document including the image for printing, the image includes one or more gray and non-gray portions. An input from a user to selectively adjust the color of the gray portions of the image is received. The gray portions of the image are identified. Then, color values associated with the identified gray portions of the image are determined. Based on the user input, the determined color values associated with the gray portions of the image are selectively adjusted, without affecting non-gray color portions of the image to generate an updated image. The updated image is printed and the printed image includes adjusted color for the gray portions of the image such that gray color in the printed image is consistent with gray color of the image in the document.

Abstract: The disclosure discloses methods and systems for securing confidential content of a document. The method includes receiving a print request to print the document. A user interface is provided to the user having a secure option, the secure option further includes a partial secure option to secure partial content of the document. Based on the selection of the partial secure option, a selection of a confidential area including the confidential content in the document is received. Based on the selection, one or more coordinates of the confidential area are calculated. Then, an infrared (IR) mark is embedded in the document. While embedding the IR mark, the one or more coordinates of the confidential area including the confidential content in the document is embedded. Finally, a printed document is output with the IR mark including the coordinates of the confidential area for later identification of the confidential content and/or use such as masking.

Abstract: The present disclosure discloses methods and systems for detecting an IR security mark in a document based on known color information and halftone frequency information. The method includes receiving a document from a user, including an IR security mark. Then, location information, color information and halftone frequency information are received from the user. The document is scanned. Based on the color information and the location information, the IR security mark is extracted from the scanned document. After this, halftone frequency information of the extracted IR security mark is verified. Based on the verification, text in the extracted IR security mark is identified and is then compared with one or more pre-stored IR security marks to ascertain whether the IR security mark in the document is an authentic security mark.

Abstract: The disclosure discloses methods and systems for automatically generating multiple scanned files when scanning a document at a multi-function device. The method includes receiving a multi-page document for scanning from a user. A user interface is provided to the user to input one or more keywords and one or more desired resolution values, where the input resolution values are different from a default resolution value set at the multi-function device. A page of the document is scanned to generate a scanned page of a default resolution value. The scanned page is checked if including the one or more input keywords. Accordingly, the default resolution value of the page is converted to the user desired resolution value. The scanning, checking, and converting are repeated till all the pages of the document are scanned. Multiple scanned files of different resolution values are automatically generated from single scan activity.

Abstract: The present disclosure discloses methods and systems for allowing a user to add one or more bookmarks while scanning a document. The method includes receiving a document for scanning from a user. Once received, a user interface is displayed to the user to select an option to add one or more bookmark to the document. The document is scanned to get scanned pages of the document. Based on the selection of the option by the user, one or more bookmarks are added to one or more scanned pages of the document. The scanned document including the one or more bookmarked pages is sent to the one or more recipients for the desired action.

Abstract: The present disclosure discloses methods and systems for automatically detecting Infrared (IR) security mark based on unknown halftone frequency information. The method includes receiving a document from a user including an IR security mark. The document is scanned. Then, one or more halftone frequencies associated with the IR security mark portion are estimated. Based on the estimation, the IR security mark portion is classified into a background region and the IR marked region including the IR security mark. The IR security mark is extracted and pixels falling in the IR marked region are reconstructed to identify content in the IR security mark. Finally, the identified content is compared with one or more pre-stored IR security marks to ascertain the presence of the IR security mark in the document for further assessment. This way, the method automatically detects the IR security mark in the document.

Abstract: Disclosed is a convolution operator system for performing a convolution operation concurrently on an image. An input router receives image data. A controller allocates image data to a set of computing blocks based on the size of the image data and number of available computing blocks. Each computing block produces a convolution output corresponding to each row of the image. The controller allocates a plurality of group having one or more computing blocks to generate a set of convolution output. Further, a pipeline adder aggregates the set of convolution output to produce an aggregated convolution output. An output router transmits either the convolution output or the aggregated convolution output for performing subsequent convolution operation to generate a convolution result for the image data.

Abstract: The disclosure discloses methods and systems for automatically generating multiple scanned files when scanning a document at a multi-function device. The method includes receiving a multi-page document for scanning from a user. A user interface is provided to the user to input one or more keywords and one or more desired resolution values, where the input resolution values are different from a default resolution value set at the multi-function device. A page of the document is scanned to generate a scanned page of a default resolution value. The scanned page is checked if including the one or more input keywords. Accordingly, the default resolution value of the page is converted to the user desired resolution value. The scanning, checking, and converting are repeated till all the pages of the document are scanned. Multiple scanned files of different resolution values are automatically generated from single scan activity.

Abstract: A Convolution Multiply and Accumulate-Xtended (CMAC-X) system (102) for performing a convolution operation with functional safety mechanism is disclosed. The CMAC-X system (102) receives image data pertaining to an image. The image data comprises a set of feature matrix, a kernel size and depth information. Further, the CMAC-X system (102) generates a convoluted data based on convolution operation for each feature matrix, The CMAC-X system (102) performs an accumulation of the convoluted data to generate accumulated data, when the convolution operation for each feature matrix is performed. The CMAC-X system (102) further performs an addition of a predefined value to the accumulated data to generate added data. Further, the CMAC-X system (102) filters the added data. Further, the CMAC-X system (102) comprises a functional safety unit to verify a functionality of the CMAC-X system (102), thereby performing the convolution operation of the image with functional safety mechanism.

Abstract: A Convolution Multiply and Accumulate (CMAC) system for performing a convolution operation is disclosed. The CMAC system receives image data pertaining to an image. The image data comprises a set of feature matrix, a kernel size and depth information. Further, the CMAC system generates a convoluted data based on convolution operation for each feature matrix. The CMAC system performs an accumulation of the convoluted data to generate accumulated data, when the convolution operation for each feature matrix is performed. The CMAC system further performs an addition of a predefined value to the accumulated data to generate added data. Further, the CMAC system filters the added data to provide a convolution result for the image, thereby performing the convolution operation of the image.