Business Cases

• Medical support image processing system - development

  We have developed a system to automatically detect abnormal tissue areas from HE-stained tissue images.

  In this field, pattern matching methods have been mainly used, but instead of using this, we adopt a method that uses topological geometry to extract image features.
  Compared to similar systems, the processing speed is significantly improved.

  Technologies

  • C#
  • Histogram Processing
  • Peak Extraction Algorithm
  • Labeling Algorithm
  • Shape Extraction Process
  • Convolution Integral
  • Histogram Correction
  • Automatic White Balance Correction Algorithm
  • Color Deviation Automatic Correction Algorithm

• Bayesian networks - technical survey

  Bayesian Network is a technology of modeling causal relations between stochastic variables. In this work, we surveyed

  • Inference Algorithms
  • Parameter Learning Algorithms
  • Structure Learning Algorithms

  We made a report document which can be used until implementing as software program. We also surveyed concrete applied examples of Bayesian Networks to real world.

  Mainly surveyed the following methods:

  • Message Passing Algorithm (Probability Propagation)
  • SPI Algorithm (Symbolic Probability Inference)
  • Likelihood Weighted Sampling Method
  • Parameter Learning by EM Algorithm based on Dirichlet Distribution
  • K2 Structure Learning Algorithm

  Mainly surveyed the following application examples:

  • Abnormal Identification of Aircraft Gas Turbine Engine
  • Abnormal Diagnosis of Ship Engine Room
  • Abnormal Diagnosis of Turbine Power Generator
  • Anomaly Detection of Machines by Vibrations and Sounds
  • Anomaly Detection of Auto Door
  • Anomaly Detection of Space Appliances

• Trademark similarity determining algorithms - algorithm development

  We worked with an international patent firm to develop a machine learning algorithm that automatically determines the similarity of designations based on examples of trademark designation examinations over the past decade.

  In applying for a trademark designation, it is necessary to determine whether the designation sought to be applied for is similar to an existing one. The determination of similarity is based on experience, and can be so difficult that there are sometimes differences of opinion between patent attorneys and the JPO, which has been a factor preventing automation.

  This algorithm makes it possible to evaluate similarity numerically, for example, "Amazon" and "Amason" are 80% similar, thus automating similarity judgments.

  In developing the algorithm, we used the Python library TensorFlow and deep learning technologies.

  Services using this algorithm were featured in a newspaper (Nikkei Sangyo Shimbun, December 26, 2016). It is expected to help reduce human costs in trademark registration and accelerate business.

  

  Technologies

  • Python
  • Deep Learning
  • TensorFlow

See more cases