Optimization algorithms in FMRF model-based segmentation for LIDAR data and co-registered bands

In this paper, a fuzzy Markov random field (FMRF) model is used to segment land-objects into free, grass, building, and road regions by fusing remotely, sensed LIDAR data and co-registered color bands, i.e. scanned aerial color (RGB) photo and near infra-red (NIR) photo. An FMRF model is defined as a Markov random field (MRF) model in a fuzzy domain. Three optimization algorithms in the FMRF model, i.e. Lagrange multiplier (LM), iterated conditional mode (ICM), and simulated annealing (SA), are compared with respect to the computational cost and segmentation accuracy. The results have shown that the FMRF model-based ICM algorithm balances the computational cost and segmentation accuracy in land-cover segmentation from LIDAR data and co-registered bands.

Toxic phorbol esters from Chinese Tallow (Sapium sebiferum L.Roxb.)

Toxic phorbol esters from Chinese tallow stimulate protein kinase C. Toxicon25, 1129 – 1233, 1987. — Phorbol esters were isolated from the seeds of Chinese tallow (Sapium sebiferum L. Roxb.). These compounds were based on the tigliane nuclei, 4-deoxyphorbol, 12-deoxyphorbol and 4,20-dideoxy-5-hydroxyphorbol. The pro-inflammatory activity (id50) of the pure compounds was between 0.042 and 2.6 nmoles per ear. Protein kinase C activation assays were carried out on samples of enzyme purified from mammalian brain and the activities (Ka) were in the range 76 – 176 nM. The 4,20-dideoxy-5-hydroxy analogue was inactive in both tests. Chinese tallow, which is used as a substitute for linseed oil, may represent an industrial toxic hazard in terms of both pro-inflammatory and tumour-promoting effects.

Neural network feature maps for Chinese phonemes

It has been shown through a number of experiments that neural networks can be used for a phonetic typewriter. Algorithms can be looked on as producing self-organizing feature maps which correspond to phonemes. In the Chinese language the utterance of a Chinese character consists of a very simple string of Chinese phonemes. With this as a starting point, a neural network feature map for Chinese phonemes can be built up. In this paper, feature map structures for Chinese phonemes are discussed and tested. This research on a Chinese phonetic feature map is important both for Chinese speech recognition and for building a Chinese phonetic typewriter.

On-line handwritten segmentation in linear drawings

This paper addresses the problem of tracking line segments corresponding to on-line handwritten obtained through a digitizer tablet. The approach is based on Kalman filtering to model linear portions of on-line handwritten, particularly, handwritten numerals, and to detect abrupt changes in handwritten direction underlying a model change. This approach uses a Kalman filter framework constrained by a normalized line equation, where quadratic terms are linearized through a first-order Taylor expansion. The modeling is then carried out under the assumption that the state is deterministic and time-invariant, while the detection relies on double thresholding mechanism which tests for a violation of this assumption. The first threshold is based on an approach of layout kinetics. The second one takes into account the jump in angle between the past observed direction of layout and its current direction. The method proposed enables real-time processing. To illustrate the methodology proposed, some results obtained from handwritten numerals are presented.