The Experts below are selected from a list of 7269 Experts worldwide ranked by ideXlab platform

Zhenmin Tang - One of the best experts on this subject based on the ideXlab platform.

  • Real time road sign detection based on rotational center voting and shape analysis
    2012 IEEE International Conference on Mechatronics and Automation, 2012
    Co-Authors: Dan Xu, Zhenmin Tang
    Abstract:

    We present a real time road sign detection framework based on Color Component extraction, rotational center voting and shape analysis. The Color Component extraction comes from so called Color double-opponent in human primary visual cortex in which one Color is excited and another is inhibited. For the rotational center voting, we use the pairwise gradient vectors vote for their rotational symmetry centers by which centers and scales of regular polygons can be detected. Meanwhile the points which voting to the centers will be recorded and the categories of the sign shapes can be decided by analyzing the points. The method is tested on Chinese road sign dataset which is collected ourselves and also on the UHA dataset used by many other researchers. The experiment shows that the proposed method is invariant to translation, scale, rotation and partial occlusions.

Kazutake Uehira - One of the best experts on this subject based on the ideXlab platform.

  • invisibility and readability of temporally and spatially intensity modulated metaimage for information hiding on digital signage display system
    IEEE Transactions on Industry Applications, 2019
    Co-Authors: Hiroshi Unno, Kazutake Uehira
    Abstract:

    This paper describes a display technique that enables us to invisibly embed a metaimage into a Color Component of a displayed cover image by using a temporally, spatially, Color-intensity-modulated metaimage and to extract it. We first examined invisibility in terms of Color Components for a temporally and spatially intensity-modulated metaimage in a displayed cover image. The results obtained from these experiments revealed that the invisibility with which the metaimage was embedded in the blue Color Component was much higher than that of the red and green Components. Our experiments also revealed that the red and green Components could not be used for a Color Component in which the metaimage was embedded. We also proposed and evaluated a new technique of improving the readability of an invisibly embedded metaimage in a displayed cover image captured with a video camera. The proposed technique uses two methods. A proposed method of calculating an estimated grayscale metaimage enabled us to obtain a value for the binarizing threshold from its histogram by using the correlation between Color Components in which the metaimage was either embedded or not embedded. A proposed method of calculating an estimated binary metaimage could drastically reduce noise caused by the cover image by using the obtained value of the binary threshold and size feature parameters of the embedded metaimage. The readability of the metaimage was drastically improved by using these methods.

  • Lighting technique for attaching invisible information onto real objects using temporally and spatially Color-intensity modulated light
    2019 IEEE Industry Applications Society Annual Meeting, 2019
    Co-Authors: Hiroshi Unno, Kazutake Uehira
    Abstract:

    This paper describes a lighting technique which enables us to invisibly attach information onto a real object by using illumination light and to extract the information from a video image of the object captured with a video camera. A temporally and spatially Color-intensity modulation embeds information into a Color Component of the light beam. First, we assessed the invisibility to the human eye of the information attached onto a real object visible to the human eye. The experiments showed an upper limit value of modulation amplitude that satisfied invisibility for each Color Component. The experiment results revealed that the blue Color Component had a much higher degree of invisibility than the red and green Components. We also examined the readability of the information attached to the object with a video camera when the information was embedded in the blue Color Component of the light beam. The experimental results showed a lower limit value of modulation amplitude that satisfied readability. The experimental results showed the range of modulation amplitude of intensity in the blue Color that satisfied the invisibility and readability of the information attached to the object. The results of our experiments demonstrated the effectiveness of the proposed technique.

  • invisibility and readability of temporally and spatially intensity modulated meta image for information hiding on digital signage display system
    IEEE Industry Applications Society Annual Meeting, 2018
    Co-Authors: Hiroshi Unno, Kazutake Uehira
    Abstract:

    This paper describes a display technique that can invisibly embed a meta-image in a Color Component of a displayed cover-image by using a temporally and spatially intensity modulated meta-image and extract it. We first examined invisibility in terms of Colors for a temporally and spatially intensity modulated meta-image in a displayed cover-image. The results obtained from these experiments revealed that the invisibility with which the meta-image was embedded in the blue Color Component was much higher than that of the red and green Components. We also proposed and evaluated a method of improving the readability of an invisibly embedded meta-image in a displayed cover-image captured with a video camera. The proposed method of calculating an estimated grayscale meta-image enabled us to obtain a value for the binarizing threshold from its histogram by using the correlation between Color Components in which the meta-image was either embedded or not embedded. The readability of the meta-image was drastically improved by using this method.

Dan Xu - One of the best experts on this subject based on the ideXlab platform.

  • Real time road sign detection based on rotational center voting and shape analysis
    2012 IEEE International Conference on Mechatronics and Automation, 2012
    Co-Authors: Dan Xu, Zhenmin Tang
    Abstract:

    We present a real time road sign detection framework based on Color Component extraction, rotational center voting and shape analysis. The Color Component extraction comes from so called Color double-opponent in human primary visual cortex in which one Color is excited and another is inhibited. For the rotational center voting, we use the pairwise gradient vectors vote for their rotational symmetry centers by which centers and scales of regular polygons can be detected. Meanwhile the points which voting to the centers will be recorded and the categories of the sign shapes can be decided by analyzing the points. The method is tested on Chinese road sign dataset which is collected ourselves and also on the UHA dataset used by many other researchers. The experiment shows that the proposed method is invariant to translation, scale, rotation and partial occlusions.

Hiroshi Unno - One of the best experts on this subject based on the ideXlab platform.

  • invisibility and readability of temporally and spatially intensity modulated metaimage for information hiding on digital signage display system
    IEEE Transactions on Industry Applications, 2019
    Co-Authors: Hiroshi Unno, Kazutake Uehira
    Abstract:

    This paper describes a display technique that enables us to invisibly embed a metaimage into a Color Component of a displayed cover image by using a temporally, spatially, Color-intensity-modulated metaimage and to extract it. We first examined invisibility in terms of Color Components for a temporally and spatially intensity-modulated metaimage in a displayed cover image. The results obtained from these experiments revealed that the invisibility with which the metaimage was embedded in the blue Color Component was much higher than that of the red and green Components. Our experiments also revealed that the red and green Components could not be used for a Color Component in which the metaimage was embedded. We also proposed and evaluated a new technique of improving the readability of an invisibly embedded metaimage in a displayed cover image captured with a video camera. The proposed technique uses two methods. A proposed method of calculating an estimated grayscale metaimage enabled us to obtain a value for the binarizing threshold from its histogram by using the correlation between Color Components in which the metaimage was either embedded or not embedded. A proposed method of calculating an estimated binary metaimage could drastically reduce noise caused by the cover image by using the obtained value of the binary threshold and size feature parameters of the embedded metaimage. The readability of the metaimage was drastically improved by using these methods.

  • Lighting technique for attaching invisible information onto real objects using temporally and spatially Color-intensity modulated light
    2019 IEEE Industry Applications Society Annual Meeting, 2019
    Co-Authors: Hiroshi Unno, Kazutake Uehira
    Abstract:

    This paper describes a lighting technique which enables us to invisibly attach information onto a real object by using illumination light and to extract the information from a video image of the object captured with a video camera. A temporally and spatially Color-intensity modulation embeds information into a Color Component of the light beam. First, we assessed the invisibility to the human eye of the information attached onto a real object visible to the human eye. The experiments showed an upper limit value of modulation amplitude that satisfied invisibility for each Color Component. The experiment results revealed that the blue Color Component had a much higher degree of invisibility than the red and green Components. We also examined the readability of the information attached to the object with a video camera when the information was embedded in the blue Color Component of the light beam. The experimental results showed a lower limit value of modulation amplitude that satisfied readability. The experimental results showed the range of modulation amplitude of intensity in the blue Color that satisfied the invisibility and readability of the information attached to the object. The results of our experiments demonstrated the effectiveness of the proposed technique.

  • invisibility and readability of temporally and spatially intensity modulated meta image for information hiding on digital signage display system
    IEEE Industry Applications Society Annual Meeting, 2018
    Co-Authors: Hiroshi Unno, Kazutake Uehira
    Abstract:

    This paper describes a display technique that can invisibly embed a meta-image in a Color Component of a displayed cover-image by using a temporally and spatially intensity modulated meta-image and extract it. We first examined invisibility in terms of Colors for a temporally and spatially intensity modulated meta-image in a displayed cover-image. The results obtained from these experiments revealed that the invisibility with which the meta-image was embedded in the blue Color Component was much higher than that of the red and green Components. We also proposed and evaluated a method of improving the readability of an invisibly embedded meta-image in a displayed cover-image captured with a video camera. The proposed method of calculating an estimated grayscale meta-image enabled us to obtain a value for the binarizing threshold from its histogram by using the correlation between Color Components in which the meta-image was either embedded or not embedded. The readability of the meta-image was drastically improved by using this method.

Horacio Legal Ayala - One of the best experts on this subject based on the ideXlab platform.

  • Adaptive RGB Color Lexicographical Ordering Framework Using Statistical Parameters From the Color Component Histogram
    IEEE Access, 2019
    Co-Authors: José Luis Vázquez Noguera, Christian E. Schaerer, Jacques Facon, Horacio Legal Ayala
    Abstract:

    In image filtering, the classical lexicographical ordering is a popular method that cannot be directly applied for ordering Colors in RGB Color images. This is due to the fact that each Color has similar importance and no order can be defined trivially a priori. In this work we propose an adaptive Color lexicographical ordering framework for RGB Color images where a Color pixel is transformed into a real number. This transformation is weighted by statistical parameters from each Color Component histogram and used as the main Component for Color comparison. This approach seeks to avoid the arbitrariness since the order of the Color Component priorities is defined by the information extracted from the image itself. The proposed approach was tested by applying a median filter to reduce noise and a morphological approach to local contrast enhancement. In noise reduction, we compare our method with classical ordering techniques on images with different noise levels. Results show that our proposal outperformed the state-of-the art methods according to the Mean Absolute Error (MAE) measure, especially in those scenarios with higher noise levels. In contrast enhancement, the proposed framework outperformed the classical lexicographical ordering method according to Contrast Improvement Ratio (CIR) metric, especially when increasing the contrast factor. Our proposal generates less distortion than the state-of-the art methods ordering.

  • A Color morphological ordering method based on additive and subtractive spaces
    2014 IEEE International Conference on Image Processing (ICIP), 2014
    Co-Authors: José Luis Vázquez Noguera, Horacio Legal Ayala, Christian E. Schaerer, Jacques Facon
    Abstract:

    Mathematical morphology, based on lattice theory, is a nonlinear technique. In Color image processing, it is necessary to determine a Color space and an ordering to obtain a lattice structure. The classical lexicographical ordering is a total ordering where the choice of the main Color Component is not a trivial issue. In this work, to avoid this choice, a vectorial method in additive and subtractive Color spaces is proposed. The method first consists of a pre-ordering relation based on the image local intensity and a second ordering that ensures a total ordering, in the case that the order between two pixels cannot be established. Experimental results based on morphological erosion and dilation show the proposed approach to be promising in processing Color images.