<img height="1" width="1" src="https://www.facebook.com/tr?id=5636555096421655&amp;ev=PageView&amp;noscript=1">

El Procesamiento de Imágenes lo es Todo, Incluso en la Evaluación del Esperma

AlphaGo, un programa de computadora desarrollado por Google DeepMind en Londres, se ha convertido en la palabra clave más buscada últimamente. Mientras todos quedan impresionados por los avances de la inteligencia artificial, nos enfocamos en la tecnología básica detrás de AlphaGo: el algoritmo. Según Wikipedia, un algoritmo es un conjunto de operaciones paso a paso que se realizan en matemáticas y ciencias de la computación, y también es la base de la neurociencia. Pocos han explorado las aplicaciones del algoritmo en otros aspectos de nuestra vida cotidiana, pero aquí cubriremos varios, centrándonos en el tema del procesamiento de imágenes.

Automatic Number Plate Recognition

Automatic number plate recognition (ANPR) is a technology that uses optical character recognition on images to read vehicle registration plates. In 1976, ANPR was debuted at the Police Scientific Development Branch in the UK. It is now used by police forces around the world for law enforcement purposes. It is also used for electronic toll collection on pay-per-use roads and as a method of cataloging the movements of traffic for example by highways agencies. The primary algorithms that the software requires for identifying a license plate are: place localization, plate orientation/sizing, normalization, character segmentation, optical character recognition, and syntactical/geometrical analysis.


(Source: http://www.tech-faq.com/wp-content/uploads/2009/02/automatic-number-plate-recognition.jpg)

Food and Beverage Inspection

Quality of food inspection is a labor intensive task. However, with the introduction of the machine vision (MV) this task is getting easier. MV is the technology and methods used to provide imaging-based automatic inspection and analysis for such applications as automatic inspection, process control, and robot guidance in industry. It's also an application extent of imaging and image process. Other than quality inspection, MV has been utilized by wider industries, such as healthcare, manufacture, and logistics.

Face Recognition

Even though no computer vision system matches human performance despite years of work by computer science all over the world, face recognition systems are by no means poor. As long as the algorithm is developed well enough, the system can possibly outperform human beings. If training the algorithm on the historical data sets for a long time, the recognition can be greatly enhanced. More than that, the technology can be used to recognize other species, such as cats.

(Source: http://cdni.wired.co.uk/1920x1280/g_j/google-glass-facial-recognition.jpg)

Pedestrian Detection

To enhance the quality of safety systems on the road, image processing has also been applied to developing intelligent video surveillance systems. Despite the challenges, such as various style of clothing in appearance and different possible articulations, pedestrian detection is still one of the most active research area in computer vision. Here comes the important role that algorithm plays since it involves methods for acquiring, processing, analyzing and understanding images.

Pedastrian Detection
(Source: http://www.nextplatform.com/wp-content/uploads/2015/08/ped_det.png)

Cell Counting

Cell counting is any of various methods for the counting or similar quantification of cells in the life sciences. It is mostly applied to biological and medical purposes. But in agriculture, there's an application that can benefit tons of animal breeders on sperm counts and motility. iSperm, a system developed by Aidmics Biotechnology, is one of the players in the field. Furthermore, its portability has benefited researchers who spend a lot of time collecting outdoors. At the meanwhile, this Taiwanese company is envisaged to provide a cloud space for data storage and organizing analysis reports, by which the users can draw insights to optimize their work performances.

iSperm - Cloud

 

Reference

  1. Automatic number plate recognition: Wikipedia Link
  2. The Face Recognition Algorithm That Finally Outperforms Humans: https://medium.com/the-physics-arxiv-blog/the-face-recognition-algorithm-that-finally-outperforms-humans-2c567adbf7fc#.b2lc7d6ua
  3. Bistro: A Smart Feeder Recognizes Your Cat's Face: https://www.indiegogo.com/projects/bistro-a-smart-feeder-recognizes-your-cat-s-face#/
  4. Pedestrian detection:
    https://en.wikipedia.org/wiki/Pedestrian_detection
  5. Cell counting:
    https://en.wikipedia.org/wiki/Cell_counting

 

 

About the author

iSperm mCASA