Classification of Live Moths Combining Texture, Color and Shape Primitives

Each year, insect-borne diseases kill more than one million people, and harmful insects destroy tens of billions of dollars worth of crops and livestock. At the same time, beneficial insects pollinate three-quarters of all food consumed by humans. Given the extraordinary impact of insects on human life, it is somewhat surprising that machine learning has made very little impact on understanding (and hence, controlling) insects. In this work we discuss why this is the case, and argue that a confluence of facts make the time ripe for machine learning research to reach out to the entomological community and help them solve some important problems. As a concrete example, we show how we can solve an important classification problem in commercial entomology by leveraging off recent progress in shape, color and texture measures.

I. Introduction

The impact of insects on human health and well-being are immeasurable, both in a positive and negative sense. However these complex interrelationships are not static, but changing as humans change the environment. As a simple example, consider the Spruce Bark Beetle (Dendroctonus rufipennis). Due to global warming the average temperature in Anchorage has increased 3.9 degrees Fahrenheit over the last century. This has allowed the more Beetles to survive the normally harsh winters, exploding their population and allowing them to devastate and estimated 30 million trees per year over the last few years [1]. A similar story can be told in all the Northern US states and in Canada.