This study aimed to investigate the association between the frequency of home cooking and obesity among children in Japan. We used cross-sectional data from the Adachi Child Health Impact of Living Difficulty study, a population-based sample targeting all fourth-grade students aged 9 to 10 in Adachi City, Tokyo, Japan. Frequency of home cooking was assessed by a questionnaire for 4258 caregivers and classified as high (almost every day), medium (4–5 days/week), or low (≤3 days/week). School health checkup data on height and weight were used to calculate body mass index z-scores. Overall, 2.4% and 10.8% of children were exposed to low and medium frequencies of home cooking, respectively. After adjusting for confounding factors, children with a low frequency of home cooking were 2.27 times (95% confidence interval: 1.16–4.45) more likely to be obese, compared with those with a high frequency of home cooking. After adjustment for children’s obesity-related eating behaviors (frequency of vegetable and breakfast intake and snacking habits) as potential mediating factors, the relative risk ratio of obesity became statistically non-significant (1.90; 95% confidence interval: 0.95–3.82). A low frequency of home cooking is associated with obesity among children in Japan, and this link may be explained by unhealthy eating behaviors.