Image prominence is the most important region in an image, which can cause the visual attention and response of human beings. Preferentially allocating the computer resources for the image analysis and synthesis by the significant region is of great significance to improve the image area detecting. As a preprocessing of other disciplines in image processing field, the image prominence has widely applications in image retrieval and image segmentation. Among these applications, the super-pixel segmentation significance detection algorithm based on linear spectral clustering (LSC) has achieved good results. The significance detection algorithm proposed in this paper is better than the regional contrast ratio by replacing the method of regional formation in the latter with the linear spectral clustering image is super-pixel block. After combining with the latest depth learning method, the accuracy of the significant region detecting has a great promotion. At last, the superiority and feasibility of the super-pixel segmentation detection algorithm based on linear spectral clustering are proved by the comparative test.
The multi-instance multi-label (MIML) learning is a learning framework where each example is described by a bag of instances and corresponding to a set of labels. In some studies, the algorithms are applied to natural scene image classification and have achieved satisfied performance. We design a MIML algorithm based on RBF neural network for the natural scene image classification. In the framework, we compare classification accuracy based on the existing definitions of bag distance: maximum Hausdorff, minimum Hausdorff and average Hausdorff. Although the accuracy of average Hausdorff bag distance is the highest, we find average Hausdorff bag distance to weaken the role of the minimum distance between the instances in the two bags. So we redefine the average Hausdorff bag distance by introducing an adaptive adjustment coefficient, and it can change according to the minimum distance between the instances in the two bags. Finally, the experimental results show that the enhanced algorithm has a better result than the original algorithm.
A new type BGTI with only one GTI is designed first and it could reduce PMD greatly and has much better temperature
stability compared to traditional BGTI, the channel isolation rate of single-stage structure is not enough and result in
crosstalk increasing and SNR reducing. To improve isolation rate, two cascaded BGTI are used to realize the second
filter. Simulation and experiment results show that isolation rate is improved, the bandwidth is remained and PMD also
reaches requirement design, successfully optimizing the system performance.
KEYWORDS: Fiber Bragg gratings, Sensors, Waveguides, Demultiplexers, Temperature metrology, Optical design, Channel projecting optics, Data processing, Signal detection, Temperature sensors
A Fiber Bragg Grating (FBG) sensor interrogation system using Arrayed Waveguide Gratings(AWGs) demultiplexer
is designed and studied theoretically and experimentally. By using a temperature tunable arrayed waveguide grating
(AWG), the center wavelength of the FBG sensor is successfully interrogated, with the linear temperature dependence
of the AWG transmission wavelengths. Initial results show that the proposed wavelenght interrogation technology using
AWG demultiplexer could potentially offers a low-cost, compact, and high-performance solution for the interrogation of
FBG distributed sensors and multisensor arrays.
Tunable filters with a wide tunable rang have been found wide applications and be the key component in fiber optical
communication system and fiber sensor system. It is hard to fabricate a fiber Fabry-Perot tunable filter. In this paper, the
principles of Fabry-Perot filter is introduced, and a novel tunable Fabry-Perot filter is designed and fabricated. The
fabricated process of the tunable filter is described and the transmission spectrum of tunable F-P filter in experiment is
given and discussed. The tunable F-P filter has the advantages of simple structure, low modulated voltage and cost
effectiveness. The filter can be applied to wavelength interrogation in fiber Bragg grating (FBG) sensing system to detect
the drift of the fiber Bragg wavelength.
A tunable Fourier domain mode-locked (FDML) laser is designed and realized with Semiconductor Optical Amplifier
(SOA), and laser with wide tunable range and high stability could be acquired. Applying the tunable laser to fiber grating
sensor system could improve Signal Noise Ratio and demodulation precision, enhance the ability of multiplexing and
advance the system performance.
KEYWORDS: Digital signal processing, Signal processing, Digital filtering, Telecommunications, Quantization, Space operations, Optical filters, Computer programming, Mobile communications, Algorithm development
The fundamental of QCELP speech coding technology is introduced. According to the features of TMS320C54X family DSP of TI Inc., the implementation approach of QCELP speech coding with fixed-point DSP (digital signal processor) is presented.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.