Height Estimation of Children under Five Years using Depth Images

Malnutrition is a global health crisis and is a leading cause of death among children under 5 years. Detecting malnutrition requires anthropometric measurements of weight, height, and middle-upper arm circumference. However, measuring them accurately is a challenge, especially in the global south, due to limited resources. In this work, we propose a CNN-based approach to estimate the height of standing children under 5 years from depth images collected using a smartphone. According to the SMART Methodology Manual, the acceptable accuracy for height is less than 1.4 cm. On training our deep learning model on 87131 depth images, our model achieved a mean absolute error of 1.64% on 57064 test images. For 70.3% test images, we estimated height accurately within the acceptable 1.4 cm range. Thus, our proposed solution can accurately detect stunting (low height-for-age) in standing children below 5 years of age.

I. Introduction

Malnutrition refers to an imbalance of nutrition, both under and over-nutrition. According to the World Health Organization (WHO), malnutrition is a global health crisis and is the reason behind ~45% of deaths among children under 5 [2]. The risk of malnutrition is especially high among children below the age of 5, and effective early interventions can help overcome the alarming situation. Malnutrition is categorized into undernutrition, micro-nutrient-related malnutrition, and overweight. Deficiency of nutrition, i.e. undernutrition, is the leading reason for malnutrition in the global south. It is mainly associated with poor socioeconomic conditions due to unavailability of enough food to eat, infectious diseases, and/or lack of knowledge about young child care. Undernutrition makes the children more vulnerable to other diseases as well, and increases the risk of death. There are three forms of undernutrition: wasting (low weight-for-height), stunting (low height-for-age) and underweight (low weight-for-age).