Papers by Keyword: Image Capturing

Abstract: In present paper, a DSP-based image capturing and transmitting system is described. As a shortage of peripherals on DSP, external image capturing and data transmitting components are needed in this case. A CMOS image sensor was used to capture images, and an Ethernet MAC controller with PHY was used to transmit image data. In addition, a CPLD was used as the co-controller for timing control. ARP, IP and UDP were functioning during data transmitting through Ethernet. The Driving Mechanism of two main chips and implementing of the protocols were described in detail. Images displayed on the PC show that the system provids good performance. The system is low-cost, simple and low-power.

Abstract: Real-time detecting information marked on billets is important for automatically manufacturing and management in steelworks. But due to the tough production environments in steel enterprises, capturing and identifying characters marked on hot billets have many challenges. This paper presents a real-time image capturing and segmenting method with machine vision for characters marked on hot billets, and characters area is located based on color information of images. Furthermore, considering the marked characters are often slant, we proposed a kind of characters skew correction method to adjust the alignment of characters, and then segment characters into singles for recognition. Finally, with the proposed method, we have conducted some experiments in Baosteel Company. The result shows that our method can achieve 97% segmentation rate if we select proper image acquisition device and preprocessing algorithm. Additionally, it provides a new way for steel enterprise real-time capturing and segmenting marked characters image.

Abstract: Blindness is an obstacle that is not even comprehendible for the non-blind. Many day-to-day activities may become challenging, complicated and may require much more labor for those with eye-sight problems or blindness. One of the major problems they face is understanding visual or text information which are not in the Braille form. Not every written or printed document that a blind person would like to read is available in Braille. A blind cannot read any of the handwritten documents. They feel it very difficult, while someone has to read it for them. This is the fundamental issue that we deal with, and try to solve, with a new piece of technology, which is essentially an automated text-to-audio converting pen. According to this keynote concept, any piece of text that a person would like to read/understand is converted to an audio signal. This audio signal is transmitted to the person’s ears through wireless technology such as Bluetooth. Since this technology is in the form of a pen, it is very convenient to use and is also portable. This instrument is radical and can definitely be a empowering force in a blind person’s life, and can be helpful in relieving them of their frustration of not being able to read whatever they want, thus making their life easier.

Abstract: The objective of this research is to design and fabricate a general purpose 3D digitizer based on grinding technique to completely acquire the geometry of an object, including its inner structure, and accurately create its CAD model. How the 3D digitizer works is as follows. First a thin layer of an object that is fixed in epoxy is removed by a grinder and the image of the cross section is taken by a CCD camera. The process is repeated until the images of all the cross sections of the object are captured. Then the images are stacked up by using software 3D-DOCTOR to obtain the 3D CAD model. The accuracy of the 3D digitizer developed in the research was within 0.03 mm when measuring a length of 5.50 mm and the gauge R&R percentage was 25.99%. The performance shows that the 3D digitizer is promising for use in industry.