Optical music recognition (OMR) is the field of study which seeks to use computer vision to extract musical information from images. Most OMR work focuses on music symbols (such as notes, time signatures, clefs, etc.); to date, only two prior works pay attention to chord symbols (shorthand notation commonly used in jazz and popular music lead sheets to describe the harmony of the music) in musical documents. Chord symbols lay the foundation for jazz improvisation - a sequence of chord symbols is repeated during the improvisatory section, and the soloist and accompaniment (primarily, though not exclusively) use the chord symbols to inform their choice of notes and rhythms. In order to enable downstream work on computer-based improvisation, this work seeks to identify chords and extract musical structure from images of lead sheets with chord symbols. We contribute two new datasets for the chord identification task; one of handwritten symbols collected from students at UCF, and the other of printed symbols, collected from five different real book documents. We also propose a baseline chord identification and localization technique, using an OMR + grammar + deep learning approach to identify chord symbols and their location in the musical document, and describe baseline results on the printed and handwritten datasets. We also describe an implementation of musical form reconstruction from a lead sheet image, as well as an evaluation approach using string similarity metrics.