OnQ Blog

Developer of the month: Henry Ruiz from Texas A&M

Qualcomm Developer Network November Developer of the Month is Henry Ruiz. Henry is from Cali, Colombia where he completed his Computer Systems Engineering degree from Antonio Jose Camacho University. In 2017 he completed a Master’s degree in Artificial Intelligence from the Autonomous University of Baja California (UABC). He has experience in Machine Learning, Deep Learning, Computer Vision and Artificial Intelligence. He is also a Microsoft Student Partner and a Microsoft Certified Professional Developer. Henry is currently a Research Associate at Texas A&M getting ready to start his Ph.D.

We first encountered Henry when he was a finalist in the Qualcomm Artificial Intelligence Developer Contest last year. His app, based on his work experience and now research, supports scientists, researchers, and farmers to extract physiological information from the images of plants (rice, beans and cassava to start), collected during the crop monitoring process.

What can you tell us about your research?

My research has focused on development and implementation of software and hardware solutions to allow farmers, researchers, plant breeders, and physiologists to extract crop information. Using machine learning on data collected in forms of images, or using an IoT solution, we are able to make predictions about the health of the plants, and to correlate the results with yield, biomass, etc. These characteristics are very important when selecting or discarding a varietal.

My thesis project focused on the development of a web-based image analysis platform for phenomics using open source technologies. Using this, the scientific community, researchers, and farmers can extract physiological information through an image-based crop monitoring process. This freely-available program will perform high-throughput calculations of vegetation indices.

How did you get started using Artificial intelligence in agriculture?

Prior to attending UABC and Texas A&M, I worked for the International Center of Tropical Agriculture (CIAT) in Cali, Colombia for about five years. CIAT is an institution focused on reducing hunger and poverty and improving human nutrition in the tropics through research aimed at increasing the eco-efficiency of agriculture. During that time, I was involved in different projects, where I applied computer vision and machine learning techniques to solve different problems in the field of the Crop Phenotyping.

The most important projects were:

  • Pollen Viability Evaluation Tool: in collaboration with staff from the Andean Bean Program, we created software with OpenCV and Accord.Net to automatically evaluate the pollen viability using images taken in the microscope. This software was trained with around 1000 images from viable and non-viable pollen grains, and extracted features such as width, height, color, and roundness. Different segmentation algorithms and machine learning models were evaluated.
  • Prediction Tool for appearance and color prediction in canned beans: using a trained model based on the opinion of five experts, and a set of 100 images for each class, the software infers the appearance and color using a 1-5 defined scaled. This project was developed with the support of CIAT and Michigan State University.
  • Feature Extraction tool for bean seeds: a mobile application developed on the Qualcomm Snapdragon 835 Mobile Hardware Development Kit, which takes pictures of seeds and then extracts phenotyping features for each seed.

Where do you get your inspiration?

Technical contributions in our field are relevant, but the human aspect is the most important in my opinion. I admire the work done by Bill Gates, since he has spent the last few years using technology to reach less favored people in countries that really need it. This is the main reason why I really enjoy creating solutions with social impact. On the other hand, and no less important, I thank God for giving me the wisdom to continue!

How are you using Qualcomm technologies in your products?

As mentioned above, the Feature Extraction tool for bean seeds is a mobile application developed on the Snapdragon 835 Mobile Hardware Development Kit which allows users to take a picture of a seed, and determine its phenotypic characteristics such as color, size, shape, area, perimeter, aspect ratio and texture. Additionally, the app includes a module that infers the health status of a plant based on its color. This solution also uses the FastCV library to support the image processing algorithms we implemented.

In the future I would like to include the feature of classifying beans using deep learning techniques and, make use of the Qualcomm Neural Processing SDK for AI and TensorFlow.

Anything else to share with our developer community?

As one of the finalists of the QDN artificial intelligence competition, I really recommend and enjoy working with all the tools that they offer to us developers.

You can follow Henry on his webpage, project website or LinkedIn. You can follow Qualcomm Developer Network by signing up for email updates. Interested in being a Developer of the Month – let us know!

 

Qualcomm Snapdragon and Qualcomm Neural Processing SDK are products of Qualcomm Technologies, Inc. and/or its subsidiaries.

 

Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries ("Qualcomm"). Qualcomm products mentioned within this post are offered by Qualcomm Technologies, Inc. and/or its subsidiaries. The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.