Improving object recognition with the ℓ-channel

作者：

Highlights：

• We propose a new image format RGB-l by augmenting a new channel called ℓ-channel to RGB images.

• The acquisition cost of the new channel is very cheap using a frosted glass.

• Our additional channel is refined in a novel framework solving a unified optimization problem.

• Extensive experimental results justify the effectiveness of our novel lightness channel for many recognition problems.

摘要

Highlights•We propose a new image format RGB-l by augmenting a new channel called ℓ-channel to RGB images.•The acquisition cost of the new channel is very cheap using a frosted glass.•Our additional channel is refined in a novel framework solving a unified optimization problem.•Extensive experimental results justify the effectiveness of our novel lightness channel for many recognition problems.

论文关键词：Image format,Information fusion,Scene classification,Object detection

论文评审过程：Received 8 October 2014, Revised 8 April 2015, Accepted 13 June 2015, Available online 25 June 2015, Version of Record 28 September 2015.

论文官网地址：https://doi.org/10.1016/j.patcog.2015.06.007