Showing papers on "Blackfin published in 2018"
01 Jun 2018
TL;DR: An embedded image compressing technique using the simplified Set Partitioning Hierarchical Tree algorithm implemented in the digital signal processing board Blackfin ADSP BF561 from Analog Devices, reaching an acceptable quality of the recovered image determined using the mean opinion score over user surveys and peak signal to noise ratio applied.
Abstract: This paper discusses an embedded image compressing technique using the simplified Set Partitioning Hierarchical Tree algorithm implemented in the digital signal processing board Blackfin ADSP BF561 from Analog Devices, reaching a compression of 0.5 bits per pixel an acceptable quality of the recovered image determined using the mean opinion score over user surveys and peak signal to noise ratio applied to the recovered images.
27 Mar 2018
TL;DR: This paper describes a face detection system based on the Blackfin microcomputer architecture that may be used in an Internet of Things (IoT) context and face detection is achieved in real time.
Abstract: This paper describes a face detection system based on the Blackfin microcomputer architecture that may be used in an Internet of Things (IoT) context. The face detection algorithm is based on skin detection and scanning binary images to determine the face area. Further image processing may determine the eyes and mouth in order to extract main face characteristics. The face detection algorithm may be used in context of IoT to determine the searching area for eyes and mouth (e.g. for face recognition and emotion detection). The face detection algorithm is implemented using the Visual DSP++ integrated development environment and face detection is achieved in real time.
01 Jun 2018
TL;DR: An emotion detection system based on Blackfin microcomputer architecture and Visual Analytics Tools (VAT) is described, which uses an anthropomorphic model of human face to determine optimum searching area for eyes and mouth that depend on the mood of the human subject.
Abstract: An emotion detection system based on Blackfin microcomputer architecture and Visual Analytics Tools (VAT) is described. Such systems may be used in Internet of Things. The emotion detection algorithm use an anthropomorphic model of human face to determine optimum searching area for eyes and mouth that are modeled by ellipses with variable axis depend on the mood of the human subject. The ellipses are found using a modified Hough circle transform algorithm which minimizes the computational effort. The whole emotion detection algorithm is implemented using the VAT library functions and emotion detection is achieved in real time.